Input Text,Generated Text,flag,username,timestamp "'@article{Acharya2020AnAO, author = {A. Acharya and Kartik Talamadupula and Mark A. Finlayson}, journal = {ArXiv preprint}, title = {An Atlas of Cultural Commonsense for Machine Reasoning}, url = {https://arxiv.org/abs/2009.05664}, volume = {abs/2009.05664}, year = {2020} } @book{Aho:72, address = {Englewood Cliffs, NJ}, author = {Alfred V. Aho and Jeffrey D. Ullman}, publisher = {Prentice-Hall}, title = {The Theory of Parsing, Translation and Compiling}, volume = {1}, year = {1972} } @inproceedings{Nottingham2023Embodied, title={Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling}, author={Kolby Nottingham and Prithviraj Ammanabrolu and Alane Suhr and Yejin Choi and Hannaneh Hajishirzi and Sameer Singh and Roy Fox}, booktitle={International Conference on Machine Learning (ICML)}, url={https://arxiv.org/abs/2301.12050}, year={2023} } @article{Song2022LLMPlannerFG, title={LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models}, author={Chan Hee Song and Jiaman Wu and Clay Washington and Brian M. Sadler and Wei-Lun Chao and Yu Su}, journal={ArXiv}, year={2022}, volume={abs/2212.04088} } @article{Huang2022LanguageMA, title={Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents}, author={Wenlong Huang and P. Abbeel and Deepak Pathak and Igor Mordatch}, journal={ArXiv}, year={2022}, volume={abs/2201.07207} } @article{Lin2022OnGP, title={On Grounded Planning for Embodied Tasks with Language Models}, author={Bill Yuchen Lin and Chengsong Huang and Qianchu Liu and Wenda Gu and Sam Sommerer and Xiang Ren}, journal={ArXiv}, year={2022}, volume={abs/2209.00465} } @inproceedings{saycan, title={Do As I Can, Not As I Say: Grounding Language in Robotic Affordances}, author={Michael Ahn and Anthony Brohan and Noah Brown and Yevgen Chebotar and Omar Cortes and Byron David and Chelsea Finn and Keerthana Gopalakrishnan and Karol Hausman and Alexander Herzog and Daniel Ho and Jasmine Hsu and Julian Ibarz and Brian Ichter and Alex Irpan and Eric Jang and Rosario Jauregui Ruano and Kyle Jeffrey and Sally Jesmonth and Nikhil Jayant Joshi and Ryan C. Julian and Dmitry Kalashnikov and Yuheng Kuang and Kuang-Huei Lee and Sergey Levine and Yao Lu and Linda Luu and Carolina Parada and Peter Pastor and Jornell Quiambao and Kanishka Rao and Jarek Rettinghouse and Diego M Reyes and Pierre Sermanet and Nicolas Sievers and Clayton Tan and Alexander Toshev and Vincent Vanhoucke and F. Xia and Ted Xiao and Peng Xu and Sichun Xu and Mengyuan Yan}, booktitle={Conference on Robot Learning}, year={2022} } @article{calm, title={Keep CALM and Explore: Language Models for Action Generation in Text-based Games}, author={Shunyu Yao and Rohan Rao and Matthew J. Hausknecht and Karthik Narasimhan}, journal={ArXiv}, year={2020}, volume={abs/2010.02903} } @book{Kahneman2011ThinkingFA, title={Thinking, Fast and Slow}, author={Daniel Kahneman}, year={2011} } @inproceedings{openie, title={Leveraging Linguistic Structure For Open Domain Information Extraction}, author={Gabor Angeli and Melvin Johnson and Christopher D. Manning}, booktitle={Annual Meeting of the Association for Computational Linguistics}, year={2015} } @inproceedings{kga2c, title={Graph Constrained Reinforcement Learning for Natural Language Action Spaces}, author={Prithviraj Ammanabrolu and Matthew Hausknecht}, booktitle={International Conference on Learning Representations}, year={2020}, url={https://openreview.net/forum?id=B1x6w0EtwH}, } @inproceedings{twc, title={{Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines}}, author={Keerthiram Murugesan and Mattia Atzeni and Pavan Kapanipathi and Pushkar Shukla and Sadhana Kumaravel and Gerald Tesauro and Kartik Talamadupula and Mrinmaya Sachan and Murray Campbell}, year={2021}, booktitle={Thirty Fifth AAAI Conference on Artificial Intelligence} } @article{Miech2021ThinkingFA, title={Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers}, author={Antoine Miech and Jean-Baptiste Alayrac and Ivan Laptev and Josef Sivic and Andrew Zisserman}, journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2021}, pages={9821-9831} } @article{Chung2022ScalingIL, title={Scaling Instruction-Finetuned Language Models}, author={Hyung Won Chung and Le Hou and S. Longpre and Barret Zoph and Yi Tay and William Fedus and Eric Li and Xuezhi Wang and Mostafa Dehghani and Siddhartha Brahma and Albert Webson and Shixiang Shane Gu and Zhuyun Dai and Mirac Suzgun and Xinyun Chen and Aakanksha Chowdhery and Dasha Valter and Sharan Narang and Gaurav Mishra and Adams Wei Yu and Vincent Zhao and Yanping Huang and Andrew M. Dai and Hongkun Yu and Slav Petrov and Ed Huai-hsin Chi and Jeff Dean and Jacob Devlin and Adam Roberts and Denny Zhou and Quoc V. Le and Jason Wei}, journal={ArXiv}, year={2022}, volume={abs/2210.11416} } @article{Chen2019DeepRN, title={Deep Reasoning Networks: Thinking Fast and Slow}, author={Di Chen and Yiwei Bai and Wenting Zhao and Sebastian Ament and J. Gregoire and Carla P. Gomes}, journal={ArXiv}, year={2019}, volume={abs/1906.00855} } @inproceedings{Ganapini2021ThinkingFA, title={Thinking Fast and Slow in AI: the Role of Metacognition}, author={M. B. Ganapini and Murray Campbell and F. Fabiano and L. Horesh and Jonathan Lenchner and Andrea Loreggia and Nicholas Mattei and Francesca Rossi and Biplav Srivastava and Kristen Brent Venable}, booktitle={International Conference on Machine Learning, Optimization, and Data Science}, year={2021} } @inproceedings{Booch2020ThinkingFA, title={Thinking Fast and Slow in AI}, author={Grady Booch and F. Fabiano and L. Horesh and Kiran Kate and Jonathan Lenchner and Nick Linck and Andrea Loreggia and Keerthiram Murugesan and Nicholas Mattei and Francesca Rossi and Biplav Srivastava}, booktitle={AAAI Conference on Artificial Intelligence}, year={2020} } @article{Anthony2017ThinkingFA, title={Thinking Fast and Slow with Deep Learning and Tree Search}, author={Thomas W. Anthony and Zheng Tian and David Barber}, journal={ArXiv}, year={2017}, volume={abs/1705.08439} } @inproceedings{tbc, title={How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds}, author={Prithviraj Ammanabrolu and Jack Urbanek and Margaret Li and Arthur D. Szlam and Tim Rocktaschel and Jason Weston}, booktitle={North American Chapter of the Association for Computational Linguistics}, year={2020} } @inproceedings{dt, title={Decision Transformer: Reinforcement Learning via Sequence Modeling}, author={Lili Chen and Kevin Lu and Aravind Rajeswaran and Kimin Lee and Aditya Grover and Michael Laskin and P. Abbeel and A. Srinivas and Igor Mordatch}, booktitle={Neural Information Processing Systems}, year={2021} } @article{Wang2023DescribeEP, title={Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents}, author={Zihao Wang and Shaofei Cai and Anji Liu and Xiaojian Ma and Yitao Liang}, journal={ArXiv}, year={2023}, volume={abs/2302.01560} } @article{Shridhar2020ALFWorldAT, title={ALFWorld: Aligning Text and Embodied Environments for Interactive Learning}, author={Mohit Shridhar and Xingdi Yuan and Marc-Alexandre C{\^o}t{\'e} and Yonatan Bisk and Adam Trischler and Matthew J. Hausknecht}, journal={ArXiv}, year={2020}, volume={abs/2010.03768} } @article{ai2thor, author={Eric Kolve and Roozbeh Mottaghi and Winson Han and Eli VanderBilt and Luca Weihs and Alvaro Herrasti and Daniel Gordon and Yuke Zhu and Abhinav Gupta and Ali Farhadi}, title={{AI2-THOR: An Interactive 3D Environment for Visual AI}}, journal={arXiv}, year={2017} } @inproceedings{tw, title={TextWorld: A Learning Environment for Text-based Games}, author={Marc-Alexandre C{\^o}t{\'e} and {\'A}kos K{\'a}d{\'a}r and Xingdi Yuan and Ben A. Kybartas and Tavian Barnes and Emery Fine and James Moore and Matthew J. Hausknecht and Layla El Asri and Mahmoud Adada and Wendy Tay and Adam Trischler}, booktitle={CGW@IJCAI}, year={2018} } @article{wason1974dual, title={Dual processes in reasoning?}, author={Wason, Peter C and Evans, J St BT}, journal={Cognition}, volume={3}, number={2}, pages={141--154}, year={1974}, publisher={Elsevier} } @article{react, title={ReAct: Synergizing Reasoning and Acting in Language Models}, author={Shunyu Yao and Jeffrey Zhao and Dian Yu and Nan Du and Izhak Shafran and Karthik Narasimhan and Yuan Cao}, journal={ArXiv}, year={2022}, volume={abs/2210.03629} } @article{reflexion, title={Reflexion: an autonomous agent with dynamic memory and self-reflection}, author={Noah Shinn and Beck Labash and Ashwin Gopinath}, journal={ArXiv}, year={2023}, volume={abs/2303.11366} } @article{seq2seq, title={Sequence to Sequence Learning with Neural Networks}, author={Ilya Sutskever and Oriol Vinyals and Quoc V. Le}, journal={ArXiv}, year={2014}, volume={abs/1409.3215} } @article{Torabi2018BehavioralCF, title={Behavioral Cloning from Observation}, author={Faraz Torabi and Garrett Warnell and Peter Stone}, journal={ArXiv}, year={2018}, volume={abs/1805.01954} } @article{drrn, title={Deep Reinforcement Learning with a Natural Language Action Space}, author={Ji He and Jianshu Chen and Xiaodong He and Jianfeng Gao and Lihong Li and Li Deng and Mari Ostendorf}, journal={arXiv: Artificial Intelligence}, year={2015} } @article{Reed2022AGA, title={A Generalist Agent}, author={Scott Reed and Konrad Zolna and Emilio Parisotto and Sergio Gomez Colmenarejo and Alexander Novikov and Gabriel Barth-Maron and Mai Gimenez and Yury Sulsky and Jackie Kay and Jost Tobias Springenberg and Tom Eccles and Jake Bruce and Ali Razavi and Ashley D. Edwards and Nicolas Manfred Otto Heess and Yutian Chen and Raia Hadsell and Oriol Vinyals and Mahyar Bordbar and Nando de Freitas}, journal={ArXiv}, year={2022}, volume={abs/2205.06175} } @article{Bubeck2023SparksOA, title={Sparks of Artificial General Intelligence: Early experiments with GPT-4}, author={S{\'e}bastien Bubeck and Varun Chandrasekaran and Ronen Eldan and John A. Gehrke and Eric Horvitz and Ece Kamar and Peter Lee and Yin Tat Lee and Yuan-Fang Li and Scott M. Lundberg and Harsha Nori and Hamid Palangi and Marco Tulio Ribeiro and Yi Zhang}, journal={ArXiv}, year={2023}, volume={abs/2303.12712} } @inproceedings{sw, title={ScienceWorld: Is your Agent Smarter than a 5th Grader?}, author={Ruoyao Wang and Peter Alexander Jansen and Marc-Alexandre C{\^o}t{\'e} and Prithviraj Ammanabrolu}, booktitle={Conference on Empirical Methods in Natural Language Processing}, year={2022} } @inproceedings{Lewis2020RetrievalAugmentedGF, author = {Patrick S. H. Lewis and Ethan Perez and Aleksandra Piktus and Fabio Petroni and Vladimir Karpukhin and Naman Goyal and Heinrich K{\""{u}}ttler and Mike Lewis and Wen{-}tau Yih and Tim Rockt{\""{a}}schel and Sebastian Riedel and Douwe Kiela}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/LewisPPPKGKLYR020.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks}, url = {https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html}, year = {2020} } @article{Guu2020REALMRL, title={Retrieval Augmented Language Model Pre-Training}, author={Kelvin Guu and Kenton Lee and Zora Tung and Panupong Pasupat and Ming-Wei Chang}, booktitle={ICML}, url = {https://arxiv.org/abs/2002.08909}, year={2020} } @inproceedings{Lin2021DifferentiableOC, address = {Online}, author = {Lin, Bill Yuchen and Sun, Haitian and Dhingra, Bhuwan and Zaheer, Manzil and Ren, Xiang and Cohen, William}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.366}, pages = {4611--4625}, publisher = {Association for Computational Linguistics}, title = {Differentiable Open-Ended Commonsense Reasoning}, url = {https://aclanthology.org/2021.naacl-main.366}, year = {2021} } @article{InstructGPT, author = {Long Ouyang and Jeff Wu and Xu Jiang and Diogo Almeida and Carroll L. Wainwright and Pamela Mishkin and Chong Zhang and Sandhini Agarwal and Katarina Slama and Alex Ray and John Schulman and Jacob Hilton and Fraser Kelton and Luke E. Miller and Maddie Simens and Amanda Askell and Peter Welinder and Paul Francis Christiano and Jan Leike and Ryan J. Lowe}, journal = {ArXiv}, title = {Training language models to follow instructions with human feedback}, volume = {abs/2203.02155}, year = {2022} } @article{bigbench, author = {Aarohi Srivastava and Abhinav Rastogi and Abhishek B Rao and Abu Awal Md Shoeb and Abubakar Abid and Adam Fisch and Adam R. Brown and Adam Santoro and Aditya Gupta and Adri{\`a} Garriga-Alonso and Agnieszka Kluska and Aitor Lewkowycz and Akshat Agarwal and Alethea Power and Alex Ray and Alex Warstadt and Alexander W. Kocurek and Ali Safaya and Ali Tazarv and Alice Xiang and Alicia Parrish and Allen Nie and Aman Hussain and Amanda Askell and Amanda Dsouza and Ameet Annasaheb Rahane and Anantharaman S. Iyer and Anders Johan Andreassen and Andrea Santilli and Andreas Stuhlmuller and Andrew M. Dai and Andrew D. La and Andrew Kyle Lampinen and Andy Zou and Angela Jiang and Angelica Chen and Anh Vuong and Animesh Gupta and Anna Gottardi and Antonio Norelli and Anu Venkatesh and Arash Gholamidavoodi and Arfa Tabassum and Arul Menezes and Arun Kirubarajan and Asher Mullokandov and Ashish Sabharwal and Austin Herrick and Avia Efrat and Aykut Erdem and Ayla Karakacs and Bridget R. Roberts and Bao Sheng Loe and Barret Zoph and Bartlomiej Bojanowski and Batuhan Ozyurt and Behnam Hedayatnia and Behnam Neyshabur and Benjamin Inden and Benno Stein and Berk Ekmekci and Bill Yuchen Lin and Blake Stephen Howald and Cameron Diao and Cameron Dour and Catherine Stinson and Cedrick Argueta and C'esar Ferri Ram'irez and Chandan Singh and Charles Rathkopf and Chenlin Meng and Chitta Baral and Chiyu Wu and Chris Callison-Burch and Chris Waites and Christian Voigt and Christopher D. Manning and Christopher Potts and Cindy Tatiana Ramirez and Clara Rivera and Clemencia Siro and Colin Raffel and Courtney Ashcraft and Cristina Garbacea and Damien Sileo and Daniel H Garrette and Dan Hendrycks and Dan Kilman and Dan Roth and Daniel Freeman and Daniel Khashabi and Daniel Levy and Daniel Gonz'alez and Danny Hernandez and Danqi Chen and Daphne Ippolito and Dar Gilboa and David Dohan and D. Drakard and David Jurgens and Debajyoti Datta and Deep Ganguli and Denis Emelin and Denis Kleyko and Deniz Yuret and Derek Chen and Derek Tam and Dieuwke Hupkes and Diganta Misra and Dilyar Buzan and Dimitri Coelho Mollo and Diyi Yang and Dong-Ho Lee and Ekaterina Shutova and Ekin Dogus Cubuk and Elad Segal and Eleanor Hagerman and Elizabeth Barnes and Elizabeth P. Donoway and Ellie Pavlick and Emanuele Rodol{\`a} and Emma FC Lam and Eric Chu and Eric Tang and Erkut Erdem and Ernie Chang and Ethan A. Chi and Ethan Dyer and Ethan Jerzak and Ethan Kim and Eunice Engefu Manyasi and Evgenii Zheltonozhskii and Fan Xia and Fatemeh Siar and Fernando Mart'inez-Plumed and Francesca Happ'e and François Chollet and Frieda Rong and Gaurav Mishra and Genta Indra Winata and Gerard de Melo and Germ{\'a}n Kruszewski and Giambattista Parascandolo and Giorgio Mariani and Gloria Wang and Gonzalo Jaimovitch-L'opez and Gregor Betz and Guy Gur-Ari and Hana Galijasevic and Han Sol Kim and Hannah Rashkin and Hanna Hajishirzi and Harsh Mehta and Hayden Bogar and Henry Shevlin and Hinrich Sch{\""u}tze and Hiromu Yakura and Hongming Zhang and Hubert Wong and Ian Aik-Soon Ng and Isaac Noble and Jaap Jumelet and Jack Geissinger and John Kernion and Jacob Hilton and Jaehoon Lee and Jaime Fern{\'a}ndez Fisac and J. Brooker Simon and James Koppel and James Zheng and James Zou and Jan Koco'n and Jana Thompson and Jared Kaplan and Jarema Radom and Jascha Narain Sohl-Dickstein and Jason Phang and Jason Wei and Jason Yosinski and Jekaterina Novikova and Jelle Bosscher and Jenni Marsh and Jeremy Kim and Jeroen Taal and Jesse Engel and Jesujoba Oluwadara Alabi and Jiacheng Xu and Jiaming Song and Jillian Tang and Jane W Waweru and John Burden and John Miller and John U. Balis and Jonathan Berant and Jorg Frohberg and Jos Rozen and Jos{\'e} Hern{\'a}ndez-Orallo and Joseph Boudeman and Joseph Jones and Joshua B. Tenenbaum and Joshua S. Rule and Joyce Chua and Kamil Kanclerz and Karen Livescu and Karl Krauth and Karthik Gopalakrishnan and Katerina Ignatyeva and Katja Markert and Kaustubh D. Dhole and Kevin Gimpel and Kevin Ochieng’ Omondi and Kory Wallace Mathewson and Kristen Chiafullo and Ksenia Shkaruta and Kumar Shridhar and Kyle McDonell and Kyle Richardson and Laria Reynolds and Leo Gao and Li Zhang and Liam Dugan and Lianhui Qin and Lidia Contreras-Ochando and Louis-Philippe Morency and Luca Moschella and Luca Lam and Lucy Noble and Ludwig Schmidt and Luheng He and Luis Oliveros Col'on and Luke Metz and Lutfi Kerem cSenel and Maarten Bosma and Maarten Sap and Maartje ter Hoeve and Madotto Andrea and Maheen Saleem Farooqi and Manaal Faruqui and Mantas Mazeika and Marco Baturan and Marco Marelli and Marco Maru and M Quintana and Marie Tolkiehn and Mario Giulianelli and Martha Lewis and Martin Potthast and Matthew Leavitt and Matthias Hagen and M'aty'as Schubert and Medina Baitemirova and Melissa Arnaud and Melvin Andrew McElrath and Michael A. Yee and Michael Cohen and Mi Gu and Michael I. Ivanitskiy and Michael Starritt and Michael Strube and Michal Swkedrowski and Michele Bevilacqua and Michihiro Yasunaga and Mihir Kale and Mike Cain and Mimee Xu and Mirac Suzgun and Monica Tiwari and Mohit Bansal and Moin Aminnaseri and Mor Geva and Mozhdeh Gheini and T MukundVarma and Nanyun Peng and Nathan Chi and Nayeon Lee and Neta Gur-Ari Krakover and Nicholas Cameron and Nicholas S. Roberts and Nicholas Doiron and Nikita Nangia and Niklas Deckers and Niklas Muennighoff and Nitish Shirish Keskar and Niveditha Iyer and Noah Constant and Noah Fiedel and Nuan Wen and Oliver Zhang and Omar Agha and Omar Elbaghdadi and Omer Levy and Owain Evans and Pablo Antonio Moreno Casares and Parth Doshi and Pascale Fung and Paul Pu Liang and Paul Vicol and Pegah Alipoormolabashi and Peiyuan Liao and Percy Liang and Peter W. Chang and Peter Eckersley and Phu Mon Htut and Pi-Bei Hwang and P. Milkowski and Piyush S. Patil and Pouya Pezeshkpour and Priti Oli and Qiaozhu Mei and QING LYU and Qinlang Chen and Rabin Banjade and Rachel Etta Rudolph and Raefer Gabriel and Rahel Habacker and Ram'on Risco Delgado and Rapha{\""e}l Milli{\`e}re and Rhythm Garg and Richard Barnes and Rif A. Saurous and Riku Arakawa and Robbe Raymaekers and Robert Frank and Rohan Sikand and Roman Novak and Roman Sitelew and Ronan Le Bras and Rosanne Liu and Rowan Jacobs and Rui Zhang and Ruslan Salakhutdinov and Ryan Chi and Ryan Lee and Ryan Stovall and Ryan Teehan and Rylan Yang and Sahib J. Singh and Saif M. Mohammad and Sajant Anand and Sam Dillavou and Sam Shleifer and Sam Wiseman and Samuel Gruetter and Sam Bowman and Samuel S. Schoenholz and Sanghyun Han and Sanjeev Kwatra and Sarah A. Rous and Sarik Ghazarian and Sayan Ghosh and Sean Casey and Sebastian Bischoff and Sebastian Gehrmann and Sebastian Schuster and Sepideh Sadeghi and Shadi S. Hamdan and Sharon Zhou and Shashank Srivastava and Sherry Shi and Shikhar Singh and Shima Asaadi and Shixiang Shane Gu and Shubh Pachchigar and Shubham Toshniwal and Shyam Upadhyay and Shyamolima Debnath and Siamak Shakeri and Simon Thormeyer and Simone Melzi and Siva Reddy and Sneha Priscilla Makini and Soo-hwan Lee and Spencer Bradley Torene and Sriharsha Hatwar and Stanislas Dehaene and Stefan Divic and Stefano Ermon and Stella Rose Biderman and Stephanie C. Lin and Stephen Prasad and Steven T. Piantadosi and Stuart M. Shieber and Summer Misherghi and Svetlana Kiritchenko and Swaroop Mishra and Tal Linzen and Tal Schuster and Tao Li and Tao Yu and Tariq A. Ali and Tatsuo Hashimoto and Te-Lin Wu and Theo Desbordes and Theodore Rothschild and Thomas Phan and Tianle Wang and Tiberius Nkinyili and Timo Schick and T. N. Kornev and Timothy Telleen-Lawton and Titus Tunduny and Tobias Gerstenberg and Trenton Chang and Trishala Neeraj and Tushar Khot and Tyler O. Shultz and Uri Shaham and Vedant Misra and Vera Demberg and Victoria Nyamai and Vikas Raunak and Vinay Venkatesh Ramasesh and Vinay Uday Prabhu and Vishakh Padmakumar and Vivek Srikumar and William Fedus and William Saunders and William Zhang and W Vossen and Xiang Ren and Xiaoyu F Tong and Xinyi Wu and Xudong Shen and Yadollah Yaghoobzadeh and Yair Lakretz and Yang Song and Yasaman Bahri and Ye Ji Choi and Yichi Yang and Yiding Hao and Yifu Chen and Yonatan Belinkov and Yu Hou and Yu Hou and Yushi Bai and Zachary Seid and Zhao Xinran and Zhuoye Zhao and Zi Fu Wang and Zijie J. Wang and Zirui Wang and Ziyi Wu and Sahib Singh and Uri Shaham}, journal = {ArXiv preprint}, title = {Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models}, url = {https://arxiv.org/abs/2206.04615}, volume = {abs/2206.04615}, year = {2022} } @inproceedings{Mishra2021CrossTaskGV, address = {Dublin, Ireland}, author = {Mishra, Swaroop and Khashabi, Daniel and Baral, Chitta and Hajishirzi, Hannaneh}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.244}, pages = {3470--3487}, publisher = {Association for Computational Linguistics}, title = {Cross-Task Generalization via Natural Language Crowdsourcing Instructions}, url = {https://aclanthology.org/2022.acl-long.244}, year = {2022} } @inproceedings{mishra2021cross, address = {Dublin, Ireland}, author = {Mishra, Swaroop and Khashabi, Daniel and Baral, Chitta and Hajishirzi, Hannaneh}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.244}, pages = {3470--3487}, publisher = {Association for Computational Linguistics}, title = {Cross-Task Generalization via Natural Language Crowdsourcing Instructions}, url = {https://aclanthology.org/2022.acl-long.244}, year = {2022} } @article{Wang2022BenchmarkingGV, author = {Yizhong Wang and Swaroop Mishra and Pegah Alipoormolabashi and Yeganeh Kordi and Amirreza Mirzaei and A. Arunkumar and Arjun Ashok and Arut Selvan Dhanasekaran and Atharva Naik and David Stap and Eshaan Pathak and Giannis Karamanolakis and Haizhi Gary Lai and Ishan Purohit and Ishani Mondal and Jacob Anderson and Kirby Kuznia and Krima Doshi and Maitreya Patel and Kuntal Kumar Pal and M. Moradshahi and Mihir Parmar and Mirali Purohit and Neeraj Varshney and Phani Rohitha Kaza and Pulkit Verma and Ravsehaj Singh Puri and Rushang Karia and Shailaja Keyur Sampat and Savan Doshi and Siddharth Deepak Mishra and Sujan C. Reddy and Sumanta Patro and Tanay Dixit and Xu-dong Shen and Chitta Baral and Yejin Choi and Hannaneh Hajishirzi and Noah A. Smith and Daniel Khashabi}, journal = {ArXiv}, title = {Benchmarking Generalization via In-Context Instructions on 1, 600+ Language Tasks}, volume = {abs/2204.07705}, year = {2022} } @inproceedings{Vu2020ExploringAP, address = {Online}, author = {Vu, Tu and Wang, Tong and Munkhdalai, Tsendsuren and Sordoni, Alessandro and Trischler, Adam and Mattarella-Micke, Andrew and Maji, Subhransu and Iyyer, Mohit}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.635}, pages = {7882--7926}, publisher = {Association for Computational Linguistics}, title = {Exploring and Predicting Transferability across {NLP} Tasks}, url = {https://aclanthology.org/2020.emnlp-main.635}, year = {2020} } @inproceedings{Lange2021ToSO, address = {Online and Punta Cana, Dominican Republic}, author = {Lange, Lukas and Str{\""o}tgen, Jannik and Adel, Heike and Klakow, Dietrich}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.689}, pages = {8744--8753}, publisher = {Association for Computational Linguistics}, title = {To Share or not to Share: {P}redicting Sets of Sources for Model Transfer Learning}, url = {https://aclanthology.org/2021.emnlp-main.689}, year = {2021} } @inproceedings{Padmakumar2022ExploringTR, address = {Seattle, United States}, author = {Padmakumar, Vishakh and Lausen, Leonard and Ballesteros, Miguel and Zha, Sheng and He, He and Karypis, George}, booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2022.naacl-main.183}, pages = {2542--2550}, publisher = {Association for Computational Linguistics}, title = {Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning}, url = {https://aclanthology.org/2022.naacl-main.183}, year = {2022} } @inproceedings{brown2020languages, author = {Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert{-}Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Language Models are Few-Shot Learners}, url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html}, year = {2020} } @inproceedings{Rubin2021LearningTR, address = {Seattle, United States}, author = {Rubin, Ohad and Herzig, Jonathan and Berant, Jonathan}, booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2022.naacl-main.191}, pages = {2655--2671}, publisher = {Association for Computational Linguistics}, title = {Learning To Retrieve Prompts for In-Context Learning}, url = {https://aclanthology.org/2022.naacl-main.191}, year = {2022} } @inproceedings{Wang2022TrainingDI, address = {Dublin, Ireland}, author = {Wang, Shuohang and Xu, Yichong and Fang, Yuwei and Liu, Yang and Sun, Siqi and Xu, Ruochen and Zhu, Chenguang and Zeng, Michael}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.226}, pages = {3170--3179}, publisher = {Association for Computational Linguistics}, title = {Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data}, url = {https://aclanthology.org/2022.acl-long.226}, year = {2022} } @misc{sanh2021t0, archiveprefix = {arXiv}, author = {Victor Sanh and Albert Webson and Colin Raffel and Stephen H. Bach and Lintang Sutawika and Zaid Alyafeai and Antoine Chaffin and Arnaud Stiegler and Teven Le Scao and Arun Raja and Manan Dey and M Saiful Bari and Canwen Xu and Urmish Thakker and Shanya Sharma Sharma and Eliza Szczechla and Taewoon Kim and Gunjan Chhablani and Nihal Nayak and Debajyoti Datta and Jonathan Chang and Mike Tian-Jian Jiang and Han Wang and Matteo Manica and Sheng Shen and Zheng Xin Yong and Harshit Pandey and Rachel Bawden and Thomas Wang and Trishala Neeraj and Jos Rozen and Abheesht Sharma and Andrea Santilli and Thibault Fevry and Jason Alan Fries and Ryan Teehan and Stella Biderman and Leo Gao and Tali Bers and Thomas Wolf and Alexander M. Rush}, eprint = {2110.08207}, primaryclass = {cs.LG}, title = {Multitask Prompted Training Enables Zero-Shot Task Generalization}, year = {2021} } @inproceedings{bach2022promptsource, address = {Dublin, Ireland}, author = {Bach, Stephen and Sanh, Victor and Yong, Zheng Xin and Webson, Albert and Raffel, Colin and Nayak, Nihal V. and Sharma, Abheesht and Kim, Taewoon and Bari, M Saiful and Fevry, Thibault and Alyafeai, Zaid and Dey, Manan and Santilli, Andrea and Sun, Zhiqing and Ben-david, Srulik and Xu, Canwen and Chhablani, Gunjan and Wang, Han and Fries, Jason and Al-shaibani, Maged and Sharma, Shanya and Thakker, Urmish and Almubarak, Khalid and Tang, Xiangru and Radev, Dragomir and Jiang, Mike Tian-jian and Rush, Alexander}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations}, doi = {10.18653/v1/2022.acl-demo.9}, pages = {93--104}, publisher = {Association for Computational Linguistics}, title = {{P}rompt{S}ource: An Integrated Development Environment and Repository for Natural Language Prompts}, url = {https://aclanthology.org/2022.acl-demo.9}, year = {2022} } @article{Jang2021TowardsCK, author = {Joel Jang and Seonghyeon Ye and Sohee Yang and Joongbo Shin and Janghoon Han and Gyeonghun Kim and Stanley Jungkyu Choi and Minjoon Seo}, journal = {ArXiv preprint}, title = {Towards Continual Knowledge Learning of Language Models}, url = {https://arxiv.org/abs/2110.03215}, volume = {abs/2110.03215}, year = {2021} } @article{Mitchell2021FastME, author = {Eric Mitchell and Charles Lin and Antoine Bosselut and Chelsea Finn and Christopher D. Manning}, journal = {ArXiv preprint}, title = {Fast Model Editing at Scale}, url = {https://arxiv.org/abs/2110.11309}, volume = {abs/2110.11309}, year = {2021} } @inproceedings{clif, address = {Punta Cana, Dominican Republic}, author = {Jin, Xisen and Lin, Bill Yuchen and Rostami, Mohammad and Ren, Xiang}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021}, doi = {10.18653/v1/2021.findings-emnlp.62}, pages = {714--729}, publisher = {Association for Computational Linguistics}, title = {Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning}, url = {https://aclanthology.org/2021.findings-emnlp.62}, year = {2021} } @inproceedings{Rolnick2019ExperienceRF, author = {David Rolnick and Arun Ahuja and Jonathan Schwarz and Timothy P. Lillicrap and Gregory Wayne}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/RolnickASLW19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {348--358}, timestamp = {Thu, 21 Jan 2021 15:15:19 +0100}, title = {Experience Replay for Continual Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Abstract.html}, year = {2019} } @inproceedings{Kawaguchi2020OrderedSA, author = {Kenji Kawaguchi and Haihao Lu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aistats/KawaguchiL20.bib}, booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics, {AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]}, editor = {Silvia Chiappa and Roberto Calandra}, pages = {669--679}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Mon, 29 Jun 2020 01:00:00 +0200}, title = {Ordered {SGD:} {A} New Stochastic Optimization Framework for Empirical Risk Minimization}, url = {http://proceedings.mlr.press/v108/kawaguchi20a.html}, volume = {108}, year = {2020} } @inproceedings{aribandi2022ext, author = {Vamsi Aribandi and Yi Tay and Tal Schuster and Jinfeng Rao and Huaixiu Steven Zheng and Sanket Vaibhav Mehta and Honglei Zhuang and Vinh Q. Tran and Dara Bahri and Jianmo Ni and Jai Gupta and Kai Hui and Sebastian Ruder and Donald Metzler}, booktitle = {International Conference on Learning Representations}, title = {ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning}, url = {https://openreview.net/forum?id=Vzh1BFUCiIX}, year = {2022} } @inproceedings{chen2022weighted, author = {Shuxiao Chen and Koby Crammer and Hangfeng He and Dan Roth and Weijie J Su}, booktitle = {International Conference on Learning Representations}, title = {Weighted Training for Cross-Task Learning}, url = {https://openreview.net/forum?id=ltM1RMZntpu}, year = {2022} } @article{Jiang2019AcceleratingDL, author = {Angela H. Jiang and Daniel L.-K. Wong and Giulio Zhou and David G. Andersen and Jeff Dean and Gregory R. Ganger and Gauri Joshi and Michael Kaminsky and Michael A. Kozuch and Zachary Chase Lipton and Padmanabhan Pillai}, journal = {ArXiv preprint}, title = {Accelerating Deep Learning by Focusing on the Biggest Losers}, url = {https://arxiv.org/abs/1910.00762}, volume = {abs/1910.00762}, year = {2019} } @inproceedings{Mirzadeh2020UnderstandingTR, author = {Seyed{-}Iman Mirzadeh and Mehrdad Farajtabar and Razvan Pascanu and Hassan Ghasemzadeh}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/MirzadehFPG20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Understanding the Role of Training Regimes in Continual Learning}, url = {https://proceedings.neurips.cc/paper/2020/hash/518a38cc9a0173d0b2dc088166981cf8-Abstract.html}, year = {2020} } @article{Parisi2019ContinualLL, author = {German Ignacio Parisi and Ronald Kemker and Jose L. Part and Christopher Kanan and Stefan Wermter}, journal = {Neural networks : the official journal of the International Neural Network Society}, pages = {54-71 }, title = {Continual Lifelong Learning with Neural Networks: A Review}, volume = {113}, year = {2019} } @inproceedings{OSAKA, author = {Massimo Caccia and Pau Rodr{\'{\i}}guez and Oleksiy Ostapenko and Fabrice Normandin and Min Lin and Lucas Page{-}Caccia and Issam Hadj Laradji and Irina Rish and Alexandre Lacoste and David V{\'{a}}zquez and Laurent Charlin}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/CacciaRONLPLRLV20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Fri, 14 May 2021 01:00:00 +0200}, title = {Online Fast Adaptation and Knowledge Accumulation {(OSAKA):} a New Approach to Continual Learning}, url = {https://proceedings.neurips.cc/paper/2020/hash/c0a271bc0ecb776a094786474322cb82-Abstract.html}, year = {2020} } @article{Aljundi2019OnlineCL, author = {Rahaf Aljundi and Lucas Caccia and Eugene Belilovsky and Massimo Caccia and Min Lin and Laurent Charlin and Tinne Tuytelaars}, journal = {ArXiv preprint}, title = {Online Continual Learning with Maximally Interfered Retrieval}, url = {https://arxiv.org/abs/1908.04742}, volume = {abs/1908.04742}, year = {2019} } @article{Wei2021FinetunedLM, author = {Jason Wei and Maarten Bosma and Vincent Zhao and Kelvin Guu and Adams Wei Yu and Brian Lester and Nan Du and Andrew M. Dai and Quoc V. Le}, journal = {ArXiv preprint}, title = {Finetuned Language Models Are Zero-Shot Learners}, url = {https://arxiv.org/abs/2109.01652}, volume = {abs/2109.01652}, year = {2021} } @article{ewc2017, author = {James Kirkpatrick and Razvan Pascanu and Neil C. Rabinowitz and Joel Veness and Guillaume Desjardins and Andrei A. Rusu and Kieran Milan and John Quan and Tiago Ramalho and Agnieszka Grabska-Barwinska and Demis Hassabis and Claudia Clopath and Dharshan Kumaran and Raia Hadsell}, journal = {Proceedings of the National Academy of Sciences}, pages = {3521 - 3526}, title = {Overcoming catastrophic forgetting in neural networks}, volume = {114}, year = {2017} } @inproceedings{ye-etal-2021-crossfit, address = {Online and Punta Cana, Dominican Republic}, author = {Ye, Qinyuan and Lin, Bill Yuchen and Ren, Xiang}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.572}, pages = {7163--7189}, publisher = {Association for Computational Linguistics}, title = {{C}ross{F}it: A Few-shot Learning Challenge for Cross-task Generalization in {NLP}}, url = {https://aclanthology.org/2021.emnlp-main.572}, year = {2021} } @article{Dunn2017SearchQAAN, author = {Matthew Dunn and Levent Sagun and Mike Higgins and V. Ugur G{\""u}ney and Volkan Cirik and Kyunghyun Cho}, journal = {ArXiv preprint}, title = {SearchQA: A New Q\&A Dataset Augmented with Context from a Search Engine}, url = {https://arxiv.org/abs/1704.05179}, volume = {abs/1704.05179}, year = {2017} } @inproceedings{Trischler2017NewsQAAM, address = {Vancouver, Canada}, author = {Trischler, Adam and Wang, Tong and Yuan, Xingdi and Harris, Justin and Sordoni, Alessandro and Bachman, Philip and Suleman, Kaheer}, booktitle = {Proceedings of the 2nd Workshop on Representation Learning for {NLP}}, doi = {10.18653/v1/W17-2623}, pages = {191--200}, publisher = {Association for Computational Linguistics}, title = {{N}ews{QA}: A Machine Comprehension Dataset}, url = {https://aclanthology.org/W17-2623}, year = {2017} } @inproceedings{Joshi2017TriviaQAAL, address = {Vancouver, Canada}, author = {Joshi, Mandar and Choi, Eunsol and Weld, Daniel and Zettlemoyer, Luke}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1147}, pages = {1601--1611}, publisher = {Association for Computational Linguistics}, title = {{T}rivia{QA}: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension}, url = {https://aclanthology.org/P17-1147}, year = {2017} } @inproceedings{fisch-etal-2019-mrqa, address = {Hong Kong, China}, author = {Fisch, Adam and Talmor, Alon and Jia, Robin and Seo, Minjoon and Choi, Eunsol and Chen, Danqi}, booktitle = {Proceedings of the 2nd Workshop on Machine Reading for Question Answering}, doi = {10.18653/v1/D19-5801}, pages = {1--13}, publisher = {Association for Computational Linguistics}, title = {{MRQA} 2019 Shared Task: Evaluating Generalization in Reading Comprehension}, url = {https://aclanthology.org/D19-5801}, year = {2019} } @article{anderson1984schema, author = {Anderson, Richard C and Pearson, P David}, journal = {Handbook of reading research}, pages = {255--291}, title = {A schema-theoretic view of basic processes in reading comprehension}, volume = {1}, year = {1984} } @inproceedings{Anderson2016SPICESP, author = {Anderson, Peter and Fernando, Basura and Johnson, Mark and Gould, Stephen}, booktitle = {European Conference on Computer Vision}, organization = {Springer}, pages = {382--398}, title = {Spice: Semantic propositional image caption evaluation}, year = {2016} } @article{Ando2005, acmid = {1194905}, author = {Ando, Rie Kubota and Zhang, Tong}, issn = {1532-4435}, issue_date = {12/1/2005}, journal = {Journal of Machine Learning Research}, numpages = {37}, pages = {1817--1853}, publisher = {JMLR.org}, title = {A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data}, volume = {6}, year = {2005} } @inproceedings{andrew2007scalable, author = {Andrew, Galen and Gao, Jianfeng}, booktitle = {ICML}, pages = {33--40}, title = {Scalable training of {L1}-regularized log-linear models}, year = {2007} } @inproceedings{annervaz2018learningbd, address = {New Orleans, Louisiana}, author = {K M, Annervaz and Basu Roy Chowdhury, Somnath and Dukkipati, Ambedkar}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1029}, pages = {313--322}, publisher = {Association for Computational Linguistics}, title = {Learning beyond Datasets: Knowledge Graph Augmented Neural Networks for Natural Language Processing}, url = {https://aclanthology.org/N18-1029}, year = {2018} } @book{APA:83, address = {Washington, DC}, author = {{American Psychological Association}}, publisher = {American Psychological Association}, title = {Publications Manual}, year = {1983} } @book{arbib1987schema, author = {Arbib, Michael A and Conklin, E Jeffrey and Hill, Jane C}, publisher = {Oxford University Press}, title = {From schema theory to language.}, year = {1987} } @article{arbib1992schema, author = {Arbib, Michael A}, journal = {The Encyclopedia of Artificial Intelligence}, pages = {1427--1443}, publisher = {Wiley-Interscience}, title = {Schema theory}, volume = {2}, year = {1992} } @inproceedings{asai2020learning, author = {Akari Asai and Kazuma Hashimoto and Hannaneh Hajishirzi and Richard Socher and Caiming Xiong}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/AsaiHHSX20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering}, url = {https://openreview.net/forum?id=SJgVHkrYDH}, year = {2020} } @article{axelrod1973schema, author = {Axelrod, Robert}, journal = {American political science review}, number = {4}, pages = {1248--1266}, publisher = {Cambridge University Press}, title = {Schema theory: An information processing model of perception and cognition}, volume = {67}, year = {1973} } @inproceedings{banerjee2005meteoraa, address = {Ann Arbor, Michigan}, author = {Banerjee, Satanjeev and Lavie, Alon}, booktitle = {Proceedings of the {ACL} Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization}, pages = {65--72}, publisher = {Association for Computational Linguistics}, title = {{METEOR}: An Automatic Metric for {MT} Evaluation with Improved Correlation with Human Judgments}, url = {https://aclanthology.org/W05-0909}, year = {2005} } @inproceedings{bao2020unilmv2, author = {Hangbo Bao and Li Dong and Furu Wei and Wenhui Wang and Nan Yang and Xiaodong Liu and Yu Wang and Jianfeng Gao and Songhao Piao and Ming Zhou and Hsiao{-}Wuen Hon}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/Bao0WW0L0GP0H20.bib}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, pages = {642--652}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, title = {UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training}, url = {http://proceedings.mlr.press/v119/bao20a.html}, volume = {119}, year = {2020} } @inproceedings{bastings2017graphce, address = {Copenhagen, Denmark}, author = {Bastings, Jasmijn and Titov, Ivan and Aziz, Wilker and Marcheggiani, Diego and Sima{'}an, Khalil}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D17-1209}, pages = {1957--1967}, publisher = {Association for Computational Linguistics}, title = {Graph Convolutional Encoders for Syntax-aware Neural Machine Translation}, url = {https://aclanthology.org/D17-1209}, year = {2017} } @article{Battaglia2018RelationalIB, author = {Peter W. Battaglia and Jessica B. Hamrick and Victor Bapst and Alvaro Sanchez-Gonzalez and Vin{\'i}cius Flores Zambaldi and Mateusz Malinowski and Andrea Tacchetti and David Raposo and Adam Santoro and Ryan Faulkner and Çaglar G{\""u}lçehre and Francis Song and Andrew J. Ballard and Justin Gilmer and George E. Dahl and Ashish Vaswani and Kelsey R. Allen and Charles Nash and Victoria Langston and Chris Dyer and Nicolas Heess and Daan Wierstra and Pushmeet Kohli and Matthew Botvinick and Oriol Vinyals and Yujia Li and Razvan Pascanu}, journal = {ArXiv preprint}, title = {Relational inductive biases, deep learning, and graph networks}, url = {https://arxiv.org/abs/1806.01261}, volume = {abs/1806.01261}, year = {2018} } @article{bhakthavatsalam2020genericskb, author = {Bhakthavatsalam, Sumithra and Anastasiades, Chloe and Clark, Peter}, journal = {ArXiv preprint}, title = {GenericsKB: A Knowledge Base of Generic Statements}, url = {https://arxiv.org/abs/2005.00660}, volume = {abs/2005.00660}, year = {2020} } @inproceedings{bisk2020piqa, author = {Yonatan Bisk and Rowan Zellers and Ronan LeBras and Jianfeng Gao and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/BiskZLGC20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {7432--7439}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {{PIQA:} Reasoning about Physical Commonsense in Natural Language}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6239}, year = {2020} } @inproceedings{bollacker2008freebase, author = {Bollacker, Kurt and Evans, Colin and Paritosh, Praveen and Sturge, Tim and Taylor, Jamie}, booktitle = {SIGKDD}, organization = {AcM}, pages = {1247--1250}, title = {Freebase: a collaboratively created graph database for structuring human knowledge}, year = {2008} } @inproceedings{borsch2011, address = {Canberra, Australia}, author = {B{\""o}rschinger, Benjamin and Johnson, Mark}, booktitle = {Proceedings of the Australasian Language Technology Association Workshop 2011}, pages = {10--18}, title = {A Particle Filter algorithm for {B}ayesian Wordsegmentation}, url = {https://aclanthology.org/U11-1004}, year = {2011} } @inproceedings{c14-1001, address = {Dublin, Ireland}, author = {Harper, Mary}, booktitle = {Proceedings of {COLING} 2014, the 25th International Conference on Computational Linguistics: Technical Papers}, pages = {1}, publisher = {Dublin City University and Association for Computational Linguistics}, title = {Learning from 26 Languages: Program Management and Science in the Babel Program}, url = {https://aclanthology.org/C14-1001}, year = {2014} } @article{Chandra:81, author = {Ashok K. Chandra and Dexter C. Kozen and Larry J. Stockmeyer}, journal = {Journal of the Association for Computing Machinery}, number = {1}, pages = {114--133}, title = {Alternation}, volume = {28}, year = {1981} } @inproceedings{chen2017reading, address = {Vancouver, Canada}, author = {Chen, Danqi and Fisch, Adam and Weston, Jason and Bordes, Antoine}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1171}, pages = {1870--1879}, publisher = {Association for Computational Linguistics}, title = {Reading {W}ikipedia to Answer Open-Domain Questions}, url = {https://aclanthology.org/P17-1171}, year = {2017} } @inproceedings{Chen2019CODAHAA, address = {Minneapolis, USA}, author = {Chen, Michael and D{'}Arcy, Mike and Liu, Alisa and Fernandez, Jared and Downey, Doug}, booktitle = {Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for {NLP}}, doi = {10.18653/v1/W19-2008}, pages = {63--69}, publisher = {Association for Computational Linguistics}, title = {{CODAH}: An Adversarially-Authored Question Answering Dataset for Common Sense}, url = {https://aclanthology.org/W19-2008}, year = {2019} } @inproceedings{chi-etal-2021-infoxlm, address = {Online}, author = {Chi, Zewen and Dong, Li and Wei, Furu and Yang, Nan and Singhal, Saksham and Wang, Wenhui and Song, Xia and Mao, Xian-Ling and Huang, Heyan and Zhou, Ming}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.280}, pages = {3576--3588}, publisher = {Association for Computational Linguistics}, title = {{I}nfo{XLM}: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training}, url = {https://aclanthology.org/2021.naacl-main.280}, year = {2021} } @inproceedings{kassner-etal-2021-multilingual, address = {Online}, author = {Kassner, Nora and Dufter, Philipp and Sch{\""u}tze, Hinrich}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, doi = {10.18653/v1/2021.eacl-main.284}, pages = {3250--3258}, publisher = {Association for Computational Linguistics}, title = {Multilingual {LAMA}: Investigating Knowledge in Multilingual Pretrained Language Models}, url = {https://aclanthology.org/2021.eacl-main.284}, year = {2021} } @misc{chomsky1965aspects, author = {Chomsky, Noam}, title = {Aspects of the Theory of Syntax}, year = {1965} } @article{clark2018think, author = {Clark, Peter and Cowhey, Isaac and Etzioni, Oren and Khot, Tushar and Sabharwal, Ashish and Schoenick, Carissa and Tafjord, Oyvind}, journal = {ArXiv preprint}, title = {Think you have solved question answering? try arc, the ai2 reasoning challenge}, url = {https://arxiv.org/abs/1803.05457}, volume = {abs/1803.05457}, year = {2018} } @inproceedings{clark2020electra, author = {Kevin Clark and Minh{-}Thang Luong and Quoc V. Le and Christopher D. Manning}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ClarkLLM20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{ELECTRA:} Pre-training Text Encoders as Discriminators Rather Than Generators}, url = {https://openreview.net/forum?id=r1xMH1BtvB}, year = {2020} } @article{clark2020tydi, address = {Cambridge, MA}, author = {Clark, Jonathan H. and Choi, Eunsol and Collins, Michael and Garrette, Dan and Kwiatkowski, Tom and Nikolaev, Vitaly and Palomaki, Jennimaria}, doi = {10.1162/tacl_a_00317}, journal = {Transactions of the Association for Computational Linguistics}, pages = {454--470}, publisher = {MIT Press}, title = {{T}y{D}i {QA}: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages}, url = {https://aclanthology.org/2020.tacl-1.30}, volume = {8}, year = {2020} } @article{cohen2019neural, author = {Cohen, William W and Siegler, Matthew and Hofer, Alex}, journal = {ArXiv preprint}, title = {Neural query language: A knowledge base query language for tensorflow}, url = {https://arxiv.org/abs/1905.06209}, volume = {abs/1905.06209}, year = {2019} } @inproceedings{cohen2020scalable, author = {William W. Cohen and Haitian Sun and R. Alex Hofer and Matthew Siegler}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/CohenSHS20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base}, url = {https://openreview.net/forum?id=BJlguT4YPr}, year = {2020} } @inproceedings{conneau2018xnli, address = {Brussels, Belgium}, author = {Conneau, Alexis and Rinott, Ruty and Lample, Guillaume and Williams, Adina and Bowman, Samuel and Schwenk, Holger and Stoyanov, Veselin}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1269}, pages = {2475--2485}, publisher = {Association for Computational Linguistics}, title = {{XNLI}: Evaluating Cross-lingual Sentence Representations}, url = {https://aclanthology.org/D18-1269}, year = {2018} } @inproceedings{conneau2019xlmr, address = {Online}, author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.747}, pages = {8440--8451}, publisher = {Association for Computational Linguistics}, title = {Unsupervised Cross-lingual Representation Learning at Scale}, url = {https://aclanthology.org/2020.acl-main.747}, year = {2020} } @inproceedings{das2019multi, author = {Rajarshi Das and Shehzaad Dhuliawala and Manzil Zaheer and Andrew McCallum}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/DasDZM19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering}, url = {https://openreview.net/forum?id=HkfPSh05K7}, year = {2019} } @article{davis2015commonsense, author = {Davis, Ernest and Marcus, Gary}, journal = {Communications of the ACM}, number = {9}, pages = {92--103}, publisher = {ACM New York, NY, USA}, title = {Commonsense reasoning and commonsense knowledge in artificial intelligence}, volume = {58}, year = {2015} } @inproceedings{dblp:conf/cvpr/luybp18, author = {Jiasen Lu and Jianwei Yang and Dhruv Batra and Devi Parikh}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/LuYBP18.bib}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, doi = {10.1109/CVPR.2018.00754}, pages = {7219--7228}, publisher = {{IEEE} Computer Society}, timestamp = {Wed, 06 Feb 2019 00:00:00 +0100}, title = {Neural Baby Talk}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Lu\_Neural\_Baby\_Talk\_CVPR\_2018\_paper.html}, year = {2018} } @inproceedings{devlin2019, address = {Minneapolis, Minnesota}, author = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1423}, pages = {4171--4186}, publisher = {Association for Computational Linguistics}, title = {{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding}, url = {https://aclanthology.org/N19-1423}, year = {2019} } @inproceedings{dinu2019trainingnm, address = {Florence, Italy}, author = {Dinu, Georgiana and Mathur, Prashant and Federico, Marcello and Al-Onaizan, Yaser}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1294}, pages = {3063--3068}, publisher = {Association for Computational Linguistics}, title = {Training Neural Machine Translation to Apply Terminology Constraints}, url = {https://aclanthology.org/P19-1294}, year = {2019} } @inproceedings{dong2019unifiedlm, author = {Li Dong and Nan Yang and Wenhui Wang and Furu Wei and Xiaodong Liu and Yu Wang and Jianfeng Gao and Ming Zhou and Hsiao{-}Wuen Hon}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/00040WWLWGZH19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {13042--13054}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Unified Language Model Pre-training for Natural Language Understanding and Generation}, url = {https://proceedings.neurips.cc/paper/2019/hash/c20bb2d9a50d5ac1f713f8b34d9aac5a-Abstract.html}, year = {2019} } @inproceedings{dpr, address = {Online}, author = {Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.550}, pages = {6769--6781}, publisher = {Association for Computational Linguistics}, title = {Dense Passage Retrieval for Open-Domain Question Answering}, url = {https://aclanthology.org/2020.emnlp-main.550}, year = {2020} } @inproceedings{drkit, author = {Bhuwan Dhingra and Manzil Zaheer and Vidhisha Balachandran and Graham Neubig and Ruslan Salakhutdinov and William W. Cohen}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/DhingraZBNSC20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Differentiable Reasoning over a Virtual Knowledge Base}, url = {https://openreview.net/forum?id=SJxstlHFPH}, year = {2020} } @inproceedings{fan2018hierarchicalns, address = {Melbourne, Australia}, author = {Fan, Angela and Lewis, Mike and Dauphin, Yann}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1082}, pages = {889--898}, publisher = {Association for Computational Linguistics}, title = {Hierarchical Neural Story Generation}, url = {https://aclanthology.org/P18-1082}, year = {2018} } @inproceedings{feldman-el-yaniv-2019-multi, address = {Florence, Italy}, author = {Feldman, Yair and El-Yaniv, Ran}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1222}, pages = {2296--2309}, publisher = {Association for Computational Linguistics}, title = {Multi-Hop Paragraph Retrieval for Open-Domain Question Answering}, url = {https://aclanthology.org/P19-1222}, year = {2019} } @inproceedings{feng2018topictoessaygw, author = {Xiaocheng Feng and Ming Liu and Jiahao Liu and Bing Qin and Yibo Sun and Ting Liu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/FengLL0SL18.bib}, booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm, Sweden}, doi = {10.24963/ijcai.2018/567}, editor = {J{\'{e}}r{\^{o}}me Lang}, pages = {4078--4084}, publisher = {ijcai.org}, timestamp = {Sun, 25 Oct 2020 01:00:00 +0200}, title = {Topic-to-Essay Generation with Neural Networks}, url = {https://doi.org/10.24963/ijcai.2018/567}, year = {2018} } @inproceedings{feng2020scalable, address = {Online}, author = {Feng, Yanlin and Chen, Xinyue and Lin, Bill Yuchen and Wang, Peifeng and Yan, Jun and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.99}, pages = {1295--1309}, publisher = {Association for Computational Linguistics}, title = {Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering}, url = {https://aclanthology.org/2020.emnlp-main.99}, year = {2020} } @inproceedings{flickrentitiesijcv, author = {Bryan A. Plummer and Liwei Wang and Chris M. Cervantes and Juan C. Caicedo and Julia Hockenmaier and Svetlana Lazebnik}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/PlummerWCCHL15.bib}, booktitle = {2015 {IEEE} International Conference on Computer Vision, {ICCV} 2015, Santiago, Chile, December 7-13, 2015}, doi = {10.1109/ICCV.2015.303}, pages = {2641--2649}, publisher = {{IEEE} Computer Society}, timestamp = {Sat, 16 Sep 2017 01:00:00 +0200}, title = {Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models}, url = {https://doi.org/10.1109/ICCV.2015.303}, year = {2015} } @inproceedings{fu2018style, author = {Zhenxin Fu and Xiaoye Tan and Nanyun Peng and Dongyan Zhao and Rui Yan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/FuTPZY18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {663--670}, publisher = {{AAAI} Press}, timestamp = {Sat, 31 Aug 2019 01:00:00 +0200}, title = {Style Transfer in Text: Exploration and Evaluation}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17015}, year = {2018} } @article{garey1977rectilinear, author = {Garey, Michael R and Johnson, David S.}, journal = {SIAM Journal on Applied Mathematics}, number = {4}, pages = {826--834}, publisher = {SIAM}, title = {The rectilinear Steiner tree problem is NP-complete}, volume = {32}, year = {1977} } @inproceedings{geva-etal-2019-modeling, address = {Hong Kong, China}, author = {Geva, Mor and Goldberg, Yoav and Berant, Jonathan}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1107}, pages = {1161--1166}, publisher = {Association for Computational Linguistics}, title = {Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets}, url = {https://aclanthology.org/D19-1107}, year = {2019} } @inproceedings{gu-etal-2016-incorporating, address = {Berlin, Germany}, author = {Gu, Jiatao and Lu, Zhengdong and Li, Hang and Li, Victor O.K.}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1154}, pages = {1631--1640}, publisher = {Association for Computational Linguistics}, title = {Incorporating Copying Mechanism in Sequence-to-Sequence Learning}, url = {https://aclanthology.org/P16-1154}, year = {2016} } @inproceedings{gu2019levenshteint, author = {Jiatao Gu and Changhan Wang and Junbo Zhao}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/GuWZ19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {11179--11189}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Levenshtein Transformer}, url = {https://proceedings.neurips.cc/paper/2019/hash/675f9820626f5bc0afb47b57890b466e-Abstract.html}, year = {2019} } @inproceedings{guan2018storyeg, author = {Jian Guan and Yansen Wang and Minlie Huang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/GuanWH19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33016473}, pages = {6473--6480}, publisher = {{AAAI} Press}, timestamp = {Wed, 25 Sep 2019 01:00:00 +0200}, title = {Story Ending Generation with Incremental Encoding and Commonsense Knowledge}, url = {https://doi.org/10.1609/aaai.v33i01.33016473}, year = {2019} } @book{Gusfield:97, address = {Cambridge, UK}, author = {Dan Gusfield}, publisher = {Cambridge University Press}, title = {Algorithms on Strings, Trees and Sequences}, year = {1997} } @inproceedings{guu2020realm, title={Retrieval Augmented Language Model Pre-Training}, author={Kelvin Guu and Kenton Lee and Zora Tung and Panupong Pasupat and Ming-Wei Chang}, booktitle={ICML}, url = {https://arxiv.org/abs/2002.08909}, year={2020} } @inproceedings{hasler2018neuralmt, address = {New Orleans, Louisiana}, author = {Hasler, Eva and de Gispert, Adri{\`a} and Iglesias, Gonzalo and Byrne, Bill}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)}, doi = {10.18653/v1/N18-2081}, pages = {506--512}, publisher = {Association for Computational Linguistics}, title = {Neural Machine Translation Decoding with Terminology Constraints}, url = {https://aclanthology.org/N18-2081}, year = {2018} } @article{Hochreiter1997LongSM, author = {Sepp Hochreiter and J{\""u}rgen Schmidhuber}, journal = {Neural Computation}, pages = {1735-1780}, title = {Long Short-Term Memory}, volume = {9}, year = {1997} } @inproceedings{hokamp2017lexicallycd, address = {Vancouver, Canada}, author = {Hokamp, Chris and Liu, Qun}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1141}, pages = {1535--1546}, publisher = {Association for Computational Linguistics}, title = {Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search}, url = {https://aclanthology.org/P17-1141}, year = {2017} } @inproceedings{hu2017towardcg, author = {Zhiting Hu and Zichao Yang and Xiaodan Liang and Ruslan Salakhutdinov and Eric P. Xing}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/HuYLSX17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {1587--1596}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Toward Controlled Generation of Text}, url = {http://proceedings.mlr.press/v70/hu17e.html}, volume = {70}, year = {2017} } @techreport{Hu2020, abstract = {Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models , a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing. To this end, we introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders (XTREME) benchmark , a multi-task benchmark for evaluating the cross-lingual generalization capabilities of multilingual representations across 40 languages and 9 tasks. We demonstrate that while models tested on English reach human performance on many tasks, there is still a sizable gap in the performance of cross-lingually transferred models, particularly on syntactic and sentence retrieval tasks. There is also a wide spread of results across languages. We release the benchmark 1 to encourage research on cross-lingual learning methods that transfer linguistic knowledge across a diverse and representative set of languages and tasks.}, author = {Hu, Junjie and Ruder, Sebastian and Siddhant, Aditya and Neubig, Graham and Firat, Orhan and Johnson, Melvin}, file = {:C\:/Users/yuchenlin/OneDrive - University of Southern California/papers/XTREME A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization - 2020 - Hu et al.pdf:pdf}, issn = {2640-3498}, mendeley-groups = {Multilingual,general NLP}, pages = {4411--4421}, publisher = {PMLR}, title = {{XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization}}, url = {https://sites.}, year = {2020} } @inproceedings{huang-etal-2019-cosmos, address = {Hong Kong, China}, author = {Huang, Lifu and Le Bras, Ronan and Bhagavatula, Chandra and Choi, Yejin}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1243}, pages = {2391--2401}, publisher = {Association for Computational Linguistics}, title = {Cosmos {QA}: Machine Reading Comprehension with Contextual Commonsense Reasoning}, url = {https://aclanthology.org/D19-1243}, year = {2019} } @inproceedings{hudson2018compositionalan, author = {Drew A. Hudson and Christopher D. Manning}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/HudsonM18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Compositional Attention Networks for Machine Reasoning}, url = {https://openreview.net/forum?id=S1Euwz-Rb}, year = {2018} } @inproceedings{hudson2019gqaan, author = {Drew A. Hudson and Christopher D. Manning}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/HudsonM19.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019}, doi = {10.1109/CVPR.2019.00686}, pages = {6700--6709}, publisher = {Computer Vision Foundation / {IEEE}}, timestamp = {Fri, 27 Mar 2020 00:00:00 +0100}, title = {{GQA:} {A} New Dataset for Real-World Visual Reasoning and Compositional Question Answering}, url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Hudson\_GQA\_A\_New\_Dataset\_for\_Real-World\_Visual\_Reasoning\_and\_Compositional\_CVPR\_2019\_paper.html}, year = {2019} } @inproceedings{j-kurisinkel-chen-2019-set, address = {Hong Kong, China}, author = {J Kurisinkel, Litton and Chen, Nancy}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1638}, pages = {6165--6175}, publisher = {Association for Computational Linguistics}, title = {Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes}, url = {https://aclanthology.org/D19-1638}, year = {2019} } @article{jaume2018image, author = {Jaume, Guillaume and Bozorgtabar, Behzad and Ekenel, Hazim Kemal and Thiran, Jean-Philippe and Gabrani, Maria}, journal = {ArXiv preprint}, title = {Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks}, url = {https://arxiv.org/abs/1811.03830}, volume = {abs/1811.03830}, year = {2018} } @article{jiang2020can, address = {Cambridge, MA}, author = {Jiang, Zhengbao and Xu, Frank F. and Araki, Jun and Neubig, Graham}, doi = {10.1162/tacl_a_00324}, journal = {Transactions of the Association for Computational Linguistics}, pages = {423--438}, publisher = {MIT Press}, title = {How Can We Know What Language Models Know?}, url = {https://aclanthology.org/2020.tacl-1.28}, volume = {8}, year = {2020} } @inproceedings{jiang2020x, address = {Online}, author = {Jiang, Zhengbao and Anastasopoulos, Antonios and Araki, Jun and Ding, Haibo and Neubig, Graham}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.479}, pages = {5943--5959}, publisher = {Association for Computational Linguistics}, title = {{X}-{FACTR}: Multilingual Factual Knowledge Retrieval from Pretrained Language Models}, url = {https://aclanthology.org/2020.emnlp-main.479}, year = {2020} } @article{johnson1980mental, author = {Johnson-Laird, Philip N}, journal = {Cognitive science}, number = {1}, pages = {71--115}, publisher = {Elsevier}, title = {Mental models in cognitive science}, volume = {4}, year = {1980} } @article{johnson2019billion, author = {Johnson, Jeff and Douze, Matthijs and J{\'e}gou, Herv{\'e}}, journal = {IEEE Transactions on Big Data}, publisher = {IEEE}, title = {Billion-scale similarity search with GPUs}, year = {2019} } @inproceedings{kagnet-emnlp19, address = {Hong Kong, China}, author = {Lin, Bill Yuchen and Chen, Xinyue and Chen, Jamin and Ren, Xiang}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1282}, pages = {2829--2839}, publisher = {Association for Computational Linguistics}, title = {{K}ag{N}et: Knowledge-Aware Graph Networks for Commonsense Reasoning}, url = {https://aclanthology.org/D19-1282}, year = {2019} } @inproceedings{keysers2020measuring, author = {Daniel Keysers and Nathanael Sch{\""{a}}rli and Nathan Scales and Hylke Buisman and Daniel Furrer and Sergii Kashubin and Nikola Momchev and Danila Sinopalnikov and Lukasz Stafiniak and Tibor Tihon and Dmitry Tsarkov and Xiao Wang and Marc van Zee and Olivier Bousquet}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/KeysersSSBFKMSS20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Measuring Compositional Generalization: {A} Comprehensive Method on Realistic Data}, url = {https://openreview.net/forum?id=SygcCnNKwr}, year = {2020} } @inproceedings{khashabi2017learningwi, address = {Vancouver, Canada}, author = {Khashabi, Daniel and Khot, Tushar and Sabharwal, Ashish and Roth, Dan}, booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)}, doi = {10.18653/v1/K17-1010}, pages = {80--89}, publisher = {Association for Computational Linguistics}, title = {Learning What is Essential in Questions}, url = {https://aclanthology.org/K17-1010}, year = {2017} } @article{Khashabi2019OnTC, author = {Daniel Khashabi and Erfan Sadeqi Azer and Tushar Khot and Ashutosh Sabharwal and Dan Roth}, journal = {ArXiv preprint}, title = {On the Capabilities and Limitations of Reasoning for Natural Language Understanding}, url = {https://arxiv.org/abs/1901.02522}, volume = {abs/1901.02522}, year = {2019} } @inproceedings{khashabi2020unifiedqa, address = {Online}, author = {Khashabi, Daniel and Min, Sewon and Khot, Tushar and Sabharwal, Ashish and Tafjord, Oyvind and Clark, Peter and Hajishirzi, Hannaneh}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.171}, pages = {1896--1907}, publisher = {Association for Computational Linguistics}, title = {{UNIFIEDQA}: Crossing Format Boundaries with a Single {QA} System}, url = {https://aclanthology.org/2020.findings-emnlp.171}, year = {2020} } @inproceedings{khot2020qasc, author = {Tushar Khot and Peter Clark and Michal Guerquin and Peter Jansen and Ashish Sabharwal}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/KhotCGJS20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8082--8090}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {{QASC:} {A} Dataset for Question Answering via Sentence Composition}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6319}, year = {2020} } @inproceedings{kingma2015adamam, author = {Diederik P. Kingma and Jimmy Ba}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/journals/corr/KingmaB14.bib}, booktitle = {3rd International Conference on Learning Representations, {ICLR} 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings}, editor = {Yoshua Bengio and Yann LeCun}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Adam: {A} Method for Stochastic Optimization}, url = {http://arxiv.org/abs/1412.6980}, year = {2015} } @inproceedings{kipf2016semi, author = {Thomas N. Kipf and Max Welling}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/KipfW17.bib}, booktitle = {5th International Conference on Learning Representations, {ICLR} 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Semi-Supervised Classification with Graph Convolutional Networks}, url = {https://openreview.net/forum?id=SJU4ayYgl}, year = {2017} } @inproceedings{klein2017opennmtot, address = {Vancouver, Canada}, author = {Klein, Guillaume and Kim, Yoon and Deng, Yuntian and Senellart, Jean and Rush, Alexander}, booktitle = {Proceedings of {ACL} 2017, System Demonstrations}, pages = {67--72}, publisher = {Association for Computational Linguistics}, title = {{O}pen{NMT}: Open-Source Toolkit for Neural Machine Translation}, url = {https://aclanthology.org/P17-4012}, year = {2017} } @inproceedings{krishna2017dense, author = {Ranjay Krishna and Kenji Hata and Frederic Ren and Li Fei{-}Fei and Juan Carlos Niebles}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/KrishnaHRFN17.bib}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2017, Venice, Italy, October 22-29, 2017}, doi = {10.1109/ICCV.2017.83}, pages = {706--715}, publisher = {{IEEE} Computer Society}, timestamp = {Mon, 22 Jul 2019 01:00:00 +0200}, title = {Dense-Captioning Events in Videos}, url = {https://doi.org/10.1109/ICCV.2017.83}, year = {2017} } @article{kwiatkowski2019natural, address = {Cambridge, MA}, author = {Kwiatkowski, Tom and Palomaki, Jennimaria and Redfield, Olivia and Collins, Michael and Parikh, Ankur and Alberti, Chris and Epstein, Danielle and Polosukhin, Illia and Devlin, Jacob and Lee, Kenton and Toutanova, Kristina and Jones, Llion and Kelcey, Matthew and Chang, Ming-Wei and Dai, Andrew M. and Uszkoreit, Jakob and Le, Quoc and Petrov, Slav}, doi = {10.1162/tacl_a_00276}, journal = {Transactions of the Association for Computational Linguistics}, pages = {452--466}, publisher = {MIT Press}, title = {Natural Questions: A Benchmark for Question Answering Research}, url = {https://aclanthology.org/Q19-1026}, volume = {7}, year = {2019} } @inproceedings{laixlyh17, address = {Copenhagen, Denmark}, author = {Lai, Guokun and Xie, Qizhe and Liu, Hanxiao and Yang, Yiming and Hovy, Eduard}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D17-1082}, pages = {785--794}, publisher = {Association for Computational Linguistics}, title = {{RACE}: Large-scale {R}e{A}ding Comprehension Dataset From Examinations}, url = {https://aclanthology.org/D17-1082}, year = {2017} } @inproceedings{lake2018generalization, author = {Brenden M. Lake and Marco Baroni}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/LakeB18.bib}, booktitle = {Proceedings of the 35th International Conference on Machine Learning, {ICML} 2018, Stockholmsm{\""{a}}ssan, Stockholm, Sweden, July 10-15, 2018}, editor = {Jennifer G. Dy and Andreas Krause}, pages = {2879--2888}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks}, url = {http://proceedings.mlr.press/v80/lake18a.html}, volume = {80}, year = {2018} } @inproceedings{lample2019xlm, author = {Alexis Conneau and Guillaume Lample}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ConneauL19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {7057--7067}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Cross-lingual Language Model Pretraining}, url = {https://proceedings.neurips.cc/paper/2019/hash/c04c19c2c2474dbf5f7ac4372c5b9af1-Abstract.html}, year = {2019} } @inproceedings{lan2020albert, author = {Zhenzhong Lan and Mingda Chen and Sebastian Goodman and Kevin Gimpel and Piyush Sharma and Radu Soricut}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/LanCGGSS20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language Representations}, url = {https://openreview.net/forum?id=H1eA7AEtvS}, year = {2020} } @inproceedings{lee2018deterministicnn, address = {Brussels, Belgium}, author = {Lee, Jason and Mansimov, Elman and Cho, Kyunghyun}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1149}, pages = {1173--1182}, publisher = {Association for Computational Linguistics}, title = {Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement}, url = {https://aclanthology.org/D18-1149}, year = {2018} } @inproceedings{lee2019latent, address = {Florence, Italy}, author = {Lee, Kenton and Chang, Ming-Wei and Toutanova, Kristina}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1612}, pages = {6086--6096}, publisher = {Association for Computational Linguistics}, title = {Latent Retrieval for Weakly Supervised Open Domain Question Answering}, url = {https://aclanthology.org/P19-1612}, year = {2019} } @inproceedings{Levesque2011TheWS, author = {Hector J. Levesque}, booktitle = {AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning}, title = {The Winograd Schema Challenge}, year = {2011} } @inproceedings{lewis2019bart, address = {Online}, author = {Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Veselin and Zettlemoyer, Luke}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.703}, pages = {7871--7880}, publisher = {Association for Computational Linguistics}, title = {{BART}: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, url = {https://aclanthology.org/2020.acl-main.703}, year = {2020} } @inproceedings{lewis2020retrieval, author = {Patrick S. H. Lewis and Ethan Perez and Aleksandra Piktus and Fabio Petroni and Vladimir Karpukhin and Naman Goyal and Heinrich K{\""{u}}ttler and Mike Lewis and Wen{-}tau Yih and Tim Rockt{\""{a}}schel and Sebastian Riedel and Douwe Kiela}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/LewisPPPKGKLYR020.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks}, url = {https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html}, year = {2020} } @inproceedings{li2016commonsense, address = {Berlin, Germany}, author = {Li, Xiang and Taheri, Aynaz and Tu, Lifu and Gimpel, Kevin}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1137}, pages = {1445--1455}, publisher = {Association for Computational Linguistics}, title = {Commonsense Knowledge Base Completion}, url = {https://aclanthology.org/P16-1137}, year = {2016} } @inproceedings{li2018deleterg, address = {New Orleans, Louisiana}, author = {Li, Juncen and Jia, Robin and He, He and Liang, Percy}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1169}, pages = {1865--1874}, publisher = {Association for Computational Linguistics}, title = {Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer}, url = {https://aclanthology.org/N18-1169}, year = {2018} } @inproceedings{li2020bertattackaa, address = {Online}, author = {Li, Linyang and Ma, Ruotian and Guo, Qipeng and Xue, Xiangyang and Qiu, Xipeng}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.500}, pages = {6193--6202}, publisher = {Association for Computational Linguistics}, title = {{BERT}-{ATTACK}: Adversarial Attack Against {BERT} Using {BERT}}, url = {https://aclanthology.org/2020.emnlp-main.500}, year = {2020} } @inproceedings{liang2020xglue, address = {Online}, author = {Liang, Yaobo and Duan, Nan and Gong, Yeyun and Wu, Ning and Guo, Fenfei and Qi, Weizhen and Gong, Ming and Shou, Linjun and Jiang, Daxin and Cao, Guihong and Fan, Xiaodong and Zhang, Ruofei and Agrawal, Rahul and Cui, Edward and Wei, Sining and Bharti, Taroon and Qiao, Ying and Chen, Jiun-Hung and Wu, Winnie and Liu, Shuguang and Yang, Fan and Campos, Daniel and Majumder, Rangan and Zhou, Ming}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.484}, pages = {6008--6018}, publisher = {Association for Computational Linguistics}, title = {{XGLUE}: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation}, url = {https://aclanthology.org/2020.emnlp-main.484}, year = {2020} } @inproceedings{lin2004rougeap, address = {Barcelona, Spain}, author = {Lin, Chin-Yew}, booktitle = {Text Summarization Branches Out}, pages = {74--81}, publisher = {Association for Computational Linguistics}, title = {{ROUGE}: A Package for Automatic Evaluation of Summaries}, url = {https://aclanthology.org/W04-1013}, year = {2004} } @inproceedings{Lin2014MicrosoftCC, author = {Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence}, booktitle = {European conference on computer vision}, organization = {Springer}, pages = {740--755}, title = {Microsoft coco: Common objects in context}, year = {2014} } @inproceedings{lin2018miningcd, address = {Melbourne, Australia}, author = {Lin, Bill Yuchen and Xu, Frank F. and Zhu, Kenny and Hwang, Seung-won}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1066}, pages = {709--719}, publisher = {Association for Computational Linguistics}, title = {Mining Cross-Cultural Differences and Similarities in Social Media}, url = {https://aclanthology.org/P18-1066}, year = {2018} } @inproceedings{lin2019commongen, address = {Online}, author = {Lin, Bill Yuchen and Zhou, Wangchunshu and Shen, Ming and Zhou, Pei and Bhagavatula, Chandra and Choi, Yejin and Ren, Xiang}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.165}, pages = {1823--1840}, publisher = {Association for Computational Linguistics}, title = {{C}ommon{G}en: A Constrained Text Generation Challenge for Generative Commonsense Reasoning}, url = {https://aclanthology.org/2020.findings-emnlp.165}, year = {2020} } @inproceedings{lin2020birds, address = {Online}, author = {Lin, Bill Yuchen and Lee, Seyeon and Khanna, Rahul and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.557}, pages = {6862--6868}, publisher = {Association for Computational Linguistics}, title = {{B}irds have four legs?! {N}umer{S}ense: {P}robing {N}umerical {C}ommonsense {K}nowledge of {P}re-{T}rained {L}anguage {M}odels}, url = {https://aclanthology.org/2020.emnlp-main.557}, year = {2020} } @article{Liu2019RoBERTaAR, author = {Yinhan Liu and Myle Ott and Naman Goyal and Jingfei Du and Mandar Joshi and Danqi Chen and Omer Levy and Mike Lewis and Luke Zettlemoyer and Veselin Stoyanov}, journal = {ArXiv preprint}, title = {RoBERTa: A Robustly Optimized BERT Pretraining Approach}, url = {https://arxiv.org/abs/1907.11692}, volume = {abs/1907.11692}, year = {2019} } @article{lsmdc, author = {Rohrbach, Anna and Torabi, Atousa and Rohrbach, Marcus and Tandon, Niket and Pal, Christopher and Larochelle, Hugo and Courville, Aaron and Schiele, Bernt}, journal = {International Journal of Computer Vision}, number = {1}, pages = {94--120}, publisher = {Springer}, title = {Movie description}, volume = {123}, year = {2017} } @inproceedings{luo2019adr, author = {Fuli Luo and Peng Li and Jie Zhou and Pengcheng Yang and Baobao Chang and Xu Sun and Zhifang Sui}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/LuoLZYCSS19.bib}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, doi = {10.24963/ijcai.2019/711}, editor = {Sarit Kraus}, pages = {5116--5122}, publisher = {ijcai.org}, timestamp = {Wed, 22 Jan 2020 00:00:00 +0100}, title = {A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer}, url = {https://doi.org/10.24963/ijcai.2019/711}, year = {2019} } @inproceedings{luo2019towardsft, address = {Florence, Italy}, author = {Luo, Fuli and Li, Peng and Yang, Pengcheng and Zhou, Jie and Tan, Yutong and Chang, Baobao and Sui, Zhifang and Sun, Xu}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1194}, pages = {2013--2022}, publisher = {Association for Computational Linguistics}, title = {Towards Fine-grained Text Sentiment Transfer}, url = {https://aclanthology.org/P19-1194}, year = {2019} } @inproceedings{luong2015effectiveat, address = {Lisbon, Portugal}, author = {Luong, Thang and Pham, Hieu and Manning, Christopher D.}, booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D15-1166}, pages = {1412--1421}, publisher = {Association for Computational Linguistics}, title = {Effective Approaches to Attention-based Neural Machine Translation}, url = {https://aclanthology.org/D15-1166}, year = {2015} } @inproceedings{lv2020graph, author = {Shangwen Lv and Daya Guo and Jingjing Xu and Duyu Tang and Nan Duan and Ming Gong and Linjun Shou and Daxin Jiang and Guihong Cao and Songlin Hu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/LvGXTDGSJCH20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8449--8456}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6364}, year = {2020} } @inproceedings{marcheggiani2017encodingsw, address = {Copenhagen, Denmark}, author = {Marcheggiani, Diego and Titov, Ivan}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D17-1159}, pages = {1506--1515}, publisher = {Association for Computational Linguistics}, title = {Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling}, url = {https://aclanthology.org/D17-1159}, year = {2017} } @inproceedings{mariannmt, address = {Melbourne, Australia}, author = {Junczys-Dowmunt, Marcin and Grundkiewicz, Roman and Dwojak, Tomasz and Hoang, Hieu and Heafield, Kenneth and Neckermann, Tom and Seide, Frank and Germann, Ulrich and Aji, Alham Fikri and Bogoychev, Nikolay and Martins, Andr{\'e} F. T. and Birch, Alexandra}, booktitle = {Proceedings of {ACL} 2018, System Demonstrations}, doi = {10.18653/v1/P18-4020}, pages = {116--121}, publisher = {Association for Computational Linguistics}, title = {{M}arian: Fast Neural Machine Translation in {C}++}, url = {https://aclanthology.org/P18-4020}, year = {2018} } @article{mbart, address = {Cambridge, MA}, author = {Liu, Yinhan and Gu, Jiatao and Goyal, Naman and Li, Xian and Edunov, Sergey and Ghazvininejad, Marjan and Lewis, Mike and Zettlemoyer, Luke}, doi = {10.1162/tacl_a_00343}, journal = {Transactions of the Association for Computational Linguistics}, pages = {726--742}, publisher = {MIT Press}, title = {Multilingual Denoising Pre-training for Neural Machine Translation}, url = {https://aclanthology.org/2020.tacl-1.47}, volume = {8}, year = {2020} } @inproceedings{miao2018cgmhcs, author = {Ning Miao and Hao Zhou and Lili Mou and Rui Yan and Lei Li}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/MiaoZMYL19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33016834}, pages = {6834--6842}, publisher = {{AAAI} Press}, timestamp = {Wed, 09 Sep 2020 01:00:00 +0200}, title = {{CGMH:} Constrained Sentence Generation by Metropolis-Hastings Sampling}, url = {https://doi.org/10.1609/aaai.v33i01.33016834}, year = {2019} } @inproceedings{mihaylov2018canas, address = {Brussels, Belgium}, author = {Mihaylov, Todor and Clark, Peter and Khot, Tushar and Sabharwal, Ashish}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1260}, pages = {2381--2391}, publisher = {Association for Computational Linguistics}, title = {Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering}, url = {https://aclanthology.org/D18-1260}, year = {2018} } @inproceedings{mihaylov2018knowledgeablere, address = {Melbourne, Australia}, author = {Mihaylov, Todor and Frank, Anette}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1076}, pages = {821--832}, publisher = {Association for Computational Linguistics}, title = {Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge}, url = {https://aclanthology.org/P18-1076}, year = {2018} } @book{moore2013development, author = {Moore, Chris}, publisher = {Psychology Press}, title = {The development of commonsense psychology}, year = {2013} } @inproceedings{mt5, address = {Online}, author = {Xue, Linting and Constant, Noah and Roberts, Adam and Kale, Mihir and Al-Rfou, Rami and Siddhant, Aditya and Barua, Aditya and Raffel, Colin}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.41}, pages = {483--498}, publisher = {Association for Computational Linguistics}, title = {m{T}5: A Massively Multilingual Pre-trained Text-to-Text Transformer}, url = {https://aclanthology.org/2021.naacl-main.41}, year = {2021} } @inproceedings{P16-1001, address = {Berlin, Germany}, author = {Goodman, James and Vlachos, Andreas and Naradowsky, Jason}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1001}, pages = {1--11}, publisher = {Association for Computational Linguistics}, title = {Noise reduction and targeted exploration in imitation learning for {A}bstract {M}eaning {R}epresentation parsing}, url = {https://aclanthology.org/P16-1001}, year = {2016} } @inproceedings{papineni2001bleuam, address = {Philadelphia, Pennsylvania, USA}, author = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing}, booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics}, doi = {10.3115/1073083.1073135}, pages = {311--318}, publisher = {Association for Computational Linguistics}, title = {{B}leu: a Method for Automatic Evaluation of Machine Translation}, url = {https://aclanthology.org/P02-1040}, year = {2002} } @inproceedings{Papineni2002BleuAM, address = {Philadelphia, Pennsylvania, USA}, author = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing}, booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics}, doi = {10.3115/1073083.1073135}, pages = {311--318}, publisher = {Association for Computational Linguistics}, title = {{B}leu: a Method for Automatic Evaluation of Machine Translation}, url = {https://aclanthology.org/P02-1040}, year = {2002} } @inproceedings{pascanu2014howtc, author = {Razvan Pascanu and {\c{C}}aglar G{\""{u}}l{\c{c}}ehre and Kyunghyun Cho and Yoshua Bengio}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/journals/corr/PascanuGCB13.bib}, booktitle = {2nd International Conference on Learning Representations, {ICLR} 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings}, editor = {Yoshua Bengio and Yann LeCun}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {How to Construct Deep Recurrent Neural Networks}, url = {http://arxiv.org/abs/1312.6026}, year = {2014} } @inproceedings{petroni2019language, address = {Hong Kong, China}, author = {Petroni, Fabio and Rockt{\""a}schel, Tim and Riedel, Sebastian and Lewis, Patrick and Bakhtin, Anton and Wu, Yuxiang and Miller, Alexander}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1250}, pages = {2463--2473}, publisher = {Association for Computational Linguistics}, title = {Language Models as Knowledge Bases?}, url = {https://aclanthology.org/D19-1250}, year = {2019} } @inproceedings{ponti2020xcopa, address = {Online}, author = {Ponti, Edoardo Maria and Glava{\v{s}}, Goran and Majewska, Olga and Liu, Qianchu and Vuli{\'c}, Ivan and Korhonen, Anna}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.185}, pages = {2362--2376}, publisher = {Association for Computational Linguistics}, title = {{XCOPA}: A Multilingual Dataset for Causal Commonsense Reasoning}, url = {https://aclanthology.org/2020.emnlp-main.185}, year = {2020} } @inproceedings{post-vilar-2018-fast, address = {New Orleans, Louisiana}, author = {Post, Matt and Vilar, David}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1119}, pages = {1314--1324}, publisher = {Association for Computational Linguistics}, title = {Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation}, url = {https://aclanthology.org/N18-1119}, year = {2018} } @inproceedings{puduppully-etal-2017-transition, address = {Valencia, Spain}, author = {Puduppully, Ratish and Zhang, Yue and Shrivastava, Manish}, booktitle = {Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers}, pages = {643--654}, publisher = {Association for Computational Linguistics}, title = {Transition-Based Deep Input Linearization}, url = {https://aclanthology.org/E17-1061}, year = {2017} } @inproceedings{qi2019answering, address = {Hong Kong, China}, author = {Qi, Peng and Lin, Xiaowen and Mehr, Leo and Wang, Zijian and Manning, Christopher D.}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1261}, pages = {2590--2602}, publisher = {Association for Computational Linguistics}, title = {Answering Complex Open-domain Questions Through Iterative Query Generation}, url = {https://aclanthology.org/D19-1261}, year = {2019} } @inproceedings{qi2020stanza, address = {Online}, author = {Qi, Peng and Zhang, Yuhao and Zhang, Yuhui and Bolton, Jason and Manning, Christopher D.}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations}, doi = {10.18653/v1/2020.acl-demos.14}, pages = {101--108}, publisher = {Association for Computational Linguistics}, title = {{S}tanza: A Python Natural Language Processing Toolkit for Many Human Languages}, url = {https://aclanthology.org/2020.acl-demos.14}, year = {2020} } @inproceedings{qiao2019mirrorganlt, author = {Tingting Qiao and Jing Zhang and Duanqing Xu and Dacheng Tao}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/QiaoZXT19.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019}, doi = {10.1109/CVPR.2019.00160}, pages = {1505--1514}, publisher = {Computer Vision Foundation / {IEEE}}, timestamp = {Wed, 05 Feb 2020 00:00:00 +0100}, title = {MirrorGAN: Learning Text-To-Image Generation by Redescription}, url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Qiao\_MirrorGAN\_Learning\_Text-To-Image\_Generation\_by\_Redescription\_CVPR\_2019\_paper.html}, year = {2019} } @article{radford2018improving, author = {Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya}, title = {Improving language understanding by generative pre-training}, year = {2018} } @misc{radford2019language, author = {Radford, Alec and Wu, Jeff and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya}, title = {Language Models are Unsupervised Multitask Learners}, year = {2019} } @article{raffel2019exploring, author = {Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J}, journal = {ArXiv preprint}, title = {Exploring the limits of transfer learning with a unified text-to-text transformer}, url = {https://arxiv.org/abs/1910.10683}, volume = {abs/1910.10683}, year = {2019} } @inproceedings{rajani2019explainyl, address = {Florence, Italy}, author = {Rajani, Nazneen Fatema and McCann, Bryan and Xiong, Caiming and Socher, Richard}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1487}, pages = {4932--4942}, publisher = {Association for Computational Linguistics}, title = {Explain Yourself! Leveraging Language Models for Commonsense Reasoning}, url = {https://aclanthology.org/P19-1487}, year = {2019} } @inproceedings{rajpurkar2016squad10, address = {Austin, Texas}, author = {Rajpurkar, Pranav and Zhang, Jian and Lopyrev, Konstantin and Liang, Percy}, booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D16-1264}, pages = {2383--2392}, publisher = {Association for Computational Linguistics}, title = {{SQ}u{AD}: 100,000+ Questions for Machine Comprehension of Text}, url = {https://aclanthology.org/D16-1264}, year = {2016} } @article{Schick2023ToolformerLM, title={Toolformer: Language Models Can Teach Themselves to Use Tools}, author={Timo Schick and Jane Dwivedi-Yu and Roberto Dess{\`i} and Roberta Raileanu and Maria Lomeli and Luke Zettlemoyer and Nicola Cancedda and Thomas Scialom}, journal={ArXiv}, year = {2023}, volume={abs/2302.04761} } @article{interactiveNLP, title={Interactive Natural Language Processing}, author={Zekun Wang and Ge Zhang and Kexin Yang and Ning Shi and Wangchunshu Zhou and Shaochun Hao and Guangzheng Xiong and Yizhi Li and Mong Yuan Sim and Xiuying Chen and Qingqing Zhu and Zhenzhu Yang and Adam Nik and Qi Liu and Chenghua Lin and Shi Wang and Ruibo Liu and Wenhu Chen and Ke Xu and Dayiheng Liu and Yike Guo and Jie Fu}, journal={ArXiv}, year = {2023}, } @article{Lu2023ChameleonPC, title={Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models}, author={Pan Lu and Baolin Peng and Hao Cheng and Michel Galley and Kai-Wei Chang and Ying Nian Wu and Song-Chun Zhu and Jianfeng Gao}, journal={ArXiv}, year = {2023}, volume={abs/2304.09842} } @article{openagi, title={OpenAGI: When LLM Meets Domain Experts}, author={Ge, Yingqiang and Hua, Wenyue and Ji, Jianchao and Tan, Juntao and Xu, Shuyuan and Zhang, Yongfeng}, journal={arXiv}, year = {2023}, } @article{Shen2023HuggingGPTSA, title={HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace}, author={Yongliang Shen and Kaitao Song and Xu Tan and Dong Sheng Li and Weiming Lu and Yue Ting Zhuang}, journal={ArXiv}, year={2023}, volume={abs/2303.17580} } @inproceedings{reimers2019sentencebertse, address = {Hong Kong, China}, author = {Reimers, Nils and Gurevych, Iryna}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1410}, pages = {3982--3992}, publisher = {Association for Computational Linguistics}, title = {Sentence-{BERT}: Sentence Embeddings using {S}iamese {BERT}-Networks}, url = {https://aclanthology.org/D19-1410}, year = {2019} } @inproceedings{roberts2020much, address = {Online}, author = {Roberts, Adam and Raffel, Colin and Shazeer, Noam}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.437}, pages = {5418--5426}, publisher = {Association for Computational Linguistics}, title = {How Much Knowledge Can You Pack Into the Parameters of a Language Model?}, url = {https://aclanthology.org/2020.emnlp-main.437}, year = {2020} } @inproceedings{Sakaguchi2019WINOGRANDEAA, author = {Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/SakaguchiBBC20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8732--8740}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {WinoGrande: An Adversarial Winograd Schema Challenge at Scale}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6399}, year = {2020} } @inproceedings{salazar2020maskedlm, address = {Online}, author = {Salazar, Julian and Liang, Davis and Nguyen, Toan Q. and Kirchhoff, Katrin}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.240}, pages = {2699--2712}, publisher = {Association for Computational Linguistics}, title = {Masked Language Model Scoring}, url = {https://aclanthology.org/2020.acl-main.240}, year = {2020} } @article{salton1988term, author = {Salton, Gerard and Buckley, Christopher}, journal = {Information processing \& management}, number = {5}, pages = {513--523}, publisher = {Elsevier}, title = {Term-weighting approaches in automatic text retrieval}, volume = {24}, year = {1988} } @article{Sanh2019DistilBERTAD, author = {Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf}, journal = {ArXiv preprint}, title = {DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter}, url = {https://arxiv.org/abs/1910.01108}, volume = {abs/1910.01108}, year = {2019} } @inproceedings{santoro2017asn, author = {Adam Santoro and David Raposo and David G. T. Barrett and Mateusz Malinowski and Razvan Pascanu and Peter W. Battaglia and Tim Lillicrap}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SantoroRBMPBL17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {4967--4976}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {A simple neural network module for relational reasoning}, url = {https://proceedings.neurips.cc/paper/2017/hash/e6acf4b0f69f6f6e60e9a815938aa1ff-Abstract.html}, year = {2017} } @inproceedings{sap-etal-2019-social, address = {Hong Kong, China}, author = {Sap, Maarten and Rashkin, Hannah and Chen, Derek and Le Bras, Ronan and Choi, Yejin}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1454}, pages = {4463--4473}, publisher = {Association for Computational Linguistics}, title = {Social {IQ}a: Commonsense Reasoning about Social Interactions}, url = {https://aclanthology.org/D19-1454}, year = {2019} } @inproceedings{sap2018atomic, author = {Maarten Sap and Ronan Le Bras and Emily Allaway and Chandra Bhagavatula and Nicholas Lourie and Hannah Rashkin and Brendan Roof and Noah A. Smith and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/SapBABLRRSC19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33013027}, pages = {3027--3035}, publisher = {{AAAI} Press}, timestamp = {Thu, 13 Aug 2020 01:00:00 +0200}, title = {{ATOMIC:} An Atlas of Machine Commonsense for If-Then Reasoning}, url = {https://doi.org/10.1609/aaai.v33i01.33013027}, year = {2019} } @inproceedings{scann, author = {Ruiqi Guo and Philip Sun and Erik Lindgren and Quan Geng and David Simcha and Felix Chern and Sanjiv Kumar}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/GuoSLGSCK20.bib}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, pages = {3887--3896}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, title = {Accelerating Large-Scale Inference with Anisotropic Vector Quantization}, url = {http://proceedings.mlr.press/v119/guo20h.html}, volume = {119}, year = {2020} } @inproceedings{Schlichtkrull2018ModelingRD, author = {Michael Sejr Schlichtkrull and Thomas N. Kipf and Peter Bloem and Rianne van den Berg and Ivan Titov and Max Welling}, booktitle = {European Semantic Web Conference}, title = {Modeling Relational Data with Graph Convolutional Networks}, year = {2018} } @inproceedings{see2017gettt, address = {Vancouver, Canada}, author = {See, Abigail and Liu, Peter J. and Manning, Christopher D.}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1099}, pages = {1073--1083}, publisher = {Association for Computational Linguistics}, title = {Get To The Point: Summarization with Pointer-Generator Networks}, url = {https://aclanthology.org/P17-1099}, year = {2017} } @inproceedings{seo2019real, address = {Florence, Italy}, author = {Seo, Minjoon and Lee, Jinhyuk and Kwiatkowski, Tom and Parikh, Ankur and Farhadi, Ali and Hajishirzi, Hannaneh}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1436}, pages = {4430--4441}, publisher = {Association for Computational Linguistics}, title = {Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index}, url = {https://aclanthology.org/P19-1436}, year = {2019} } @inproceedings{sharma2018conceptualca, address = {Melbourne, Australia}, author = {Sharma, Piyush and Ding, Nan and Goodman, Sebastian and Soricut, Radu}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1238}, pages = {2556--2565}, publisher = {Association for Computational Linguistics}, title = {Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning}, url = {https://aclanthology.org/P18-1238}, year = {2018} } @article{shen2014entity, author = {Shen, Wei and Wang, Jianyong and Han, Jiawei}, journal = {TKDE}, number = {2}, pages = {443--460}, publisher = {IEEE}, title = {Entity linking with a knowledge base: Issues, techniques, and solutions}, volume = {27}, year = {2014} } @inproceedings{Singh2002OpenMC, author = {Singh, Push and Lin, Thomas and Mueller, Erik T and Lim, Grace and Perkins, Travell and Zhu, Wan Li}, booktitle = {OTM Confederated International Conferences"" On the Move to Meaningful Internet Systems""}, organization = {Springer}, pages = {1223--1237}, title = {Open Mind Common Sense: Knowledge acquisition from the general public}, year = {2002} } @inproceedings{singh2018semanticallyea, address = {Melbourne, Australia}, author = {Ribeiro, Marco Tulio and Singh, Sameer and Guestrin, Carlos}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1079}, pages = {856--865}, publisher = {Association for Computational Linguistics}, title = {Semantically Equivalent Adversarial Rules for Debugging {NLP} models}, url = {https://aclanthology.org/P18-1079}, year = {2018} } @inproceedings{snli:emnlp2015, address = {Lisbon, Portugal}, author = {Bowman, Samuel R. and Angeli, Gabor and Potts, Christopher and Manning, Christopher D.}, booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D15-1075}, pages = {632--642}, publisher = {Association for Computational Linguistics}, title = {A large annotated corpus for learning natural language inference}, url = {https://aclanthology.org/D15-1075}, year = {2015} } @inproceedings{speer2017conceptnet5a, author = {Robyn Speer and Joshua Chin and Catherine Havasi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/SpeerCH17.bib}, booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, {USA}}, editor = {Satinder P. Singh and Shaul Markovitch}, pages = {4444--4451}, publisher = {{AAAI} Press}, timestamp = {Fri, 31 May 2019 01:00:00 +0200}, title = {ConceptNet 5.5: An Open Multilingual Graph of General Knowledge}, url = {http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14972}, year = {2017} } @inproceedings{stern2019insertiontf, author = {Mitchell Stern and William Chan and Jamie Kiros and Jakob Uszkoreit}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/SternCKU19.bib}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, pages = {5976--5985}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 11 Jun 2019 01:00:00 +0200}, title = {Insertion Transformer: Flexible Sequence Generation via Insertion Operations}, url = {http://proceedings.mlr.press/v97/stern19a.html}, volume = {97}, year = {2019} } @inproceedings{sun2018open, address = {Brussels, Belgium}, author = {Sun, Haitian and Dhingra, Bhuwan and Zaheer, Manzil and Mazaitis, Kathryn and Salakhutdinov, Ruslan and Cohen, William}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1455}, pages = {4231--4242}, publisher = {Association for Computational Linguistics}, title = {Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text}, url = {https://aclanthology.org/D18-1455}, year = {2018} } @inproceedings{sun2019pullnet, address = {Hong Kong, China}, author = {Sun, Haitian and Bedrax-Weiss, Tania and Cohen, William}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1242}, pages = {2380--2390}, publisher = {Association for Computational Linguistics}, title = {{P}ull{N}et: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text}, url = {https://aclanthology.org/D19-1242}, year = {2019} } @inproceedings{susanto2020lexically, address = {Online}, author = {Susanto, Raymond Hendy and Chollampatt, Shamil and Tan, Liling}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.325}, pages = {3536--3543}, publisher = {Association for Computational Linguistics}, title = {Lexically Constrained Neural Machine Translation with {L}evenshtein Transformer}, url = {https://aclanthology.org/2020.acl-main.325}, year = {2020} } @inproceedings{sutskever2014sequencets, author = {Ilya Sutskever and Oriol Vinyals and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SutskeverVL14.bib}, booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada}, editor = {Zoubin Ghahramani and Max Welling and Corinna Cortes and Neil D. Lawrence and Kilian Q. Weinberger}, pages = {3104--3112}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Sequence to Sequence Learning with Neural Networks}, url = {https://proceedings.neurips.cc/paper/2014/hash/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html}, year = {2014} } @article{t5, author = {Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J}, journal = {Journal of Machine Learning Research}, number = {140}, pages = {1--67}, title = {Exploring the limits of transfer learning with a unified text-to-text transformer}, volume = {21}, year = {2020} } @inproceedings{Talmor2018commonsenseqaaq, address = {Minneapolis, Minnesota}, author = {Talmor, Alon and Herzig, Jonathan and Lourie, Nicholas and Berant, Jonathan}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1421}, pages = {4149--4158}, publisher = {Association for Computational Linguistics}, title = {{C}ommonsense{QA}: A Question Answering Challenge Targeting Commonsense Knowledge}, url = {https://aclanthology.org/N19-1421}, year = {2019} } @inproceedings{tandon2017webchild2, address = {Vancouver, Canada}, author = {Tandon, Niket and de Melo, Gerard and Weikum, Gerhard}, booktitle = {Proceedings of {ACL} 2017, System Demonstrations}, pages = {115--120}, publisher = {Association for Computational Linguistics}, title = {{W}eb{C}hild 2.0 : Fine-Grained Commonsense Knowledge Distillation}, url = {https://aclanthology.org/P17-4020}, year = {2017} } @inproceedings{tiedemann2016opus, address = {Riga, Latvia}, author = {Tiedemann, J{\""o}rg}, booktitle = {Proceedings of the 19th Annual Conference of the European Association for Machine Translation: Projects/Products}, publisher = {Baltic Journal of Modern Computing}, title = {{OPUS} {--} parallel corpora for everyone}, url = {https://aclanthology.org/2016.eamt-2.8}, year = {2016} } @article{Trinh2018ASM, author = {Trieu H. Trinh and Quoc V. Le}, journal = {ArXiv preprint}, title = {A Simple Method for Commonsense Reasoning}, url = {https://arxiv.org/abs/1806.02847}, volume = {abs/1806.02847}, year = {2018} } @article{trinh2019do, author = {Trieu H. Trinh and Quoc V. Le}, journal = {OpenReview}, title = {Do Language Models Have Common Sense?}, volume = {ICLR submissions}, year = {2019} } @inproceedings{vaswani2017attentionia, author = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/VaswaniSPUJGKP17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {5998--6008}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Attention is All you Need}, url = {https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html}, year = {2017} } @inproceedings{vedantam2014ciderci, author = {Ramakrishna Vedantam and C. Lawrence Zitnick and Devi Parikh}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/VedantamZP15.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2015, Boston, MA, USA, June 7-12, 2015}, doi = {10.1109/CVPR.2015.7299087}, pages = {4566--4575}, publisher = {{IEEE} Computer Society}, timestamp = {Thu, 25 May 2017 01:00:00 +0200}, title = {CIDEr: Consensus-based image description evaluation}, url = {https://doi.org/10.1109/CVPR.2015.7299087}, year = {2015} } @inproceedings{wang-etal-2019-make, address = {Florence, Italy}, author = {Wang, Cunxiang and Liang, Shuailong and Zhang, Yue and Li, Xiaonan and Gao, Tian}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1393}, pages = {4020--4026}, publisher = {Association for Computational Linguistics}, title = {Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation}, url = {https://aclanthology.org/P19-1393}, year = {2019} } @inproceedings{wang-etal-2020-semeval, address = {Barcelona (online)}, author = {Wang, Cunxiang and Liang, Shuailong and Jin, Yili and Wang, Yilong and Zhu, Xiaodan and Zhang, Yue}, booktitle = {Proceedings of the Fourteenth Workshop on Semantic Evaluation}, doi = {10.18653/v1/2020.semeval-1.39}, pages = {307--321}, publisher = {International Committee for Computational Linguistics}, title = {{S}em{E}val-2020 Task 4: Commonsense Validation and Explanation}, url = {https://aclanthology.org/2020.semeval-1.39}, year = {2020} } @inproceedings{wang2014knowledgege, author = {Zhen Wang and Jianwen Zhang and Jianlin Feng and Zheng Chen}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/WangZFC14.bib}, booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence, July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada}, editor = {Carla E. Brodley and Peter Stone}, pages = {1112--1119}, publisher = {{AAAI} Press}, timestamp = {Mon, 18 Dec 2017 00:00:00 +0100}, title = {Knowledge Graph Embedding by Translating on Hyperplanes}, url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/view/8531}, year = {2014} } @inproceedings{wang2018glue, author = {Alex Wang and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/WangSMHLB19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {{GLUE:} {A} Multi-Task Benchmark and Analysis Platform for Natural Language Understanding}, url = {https://openreview.net/forum?id=rJ4km2R5t7}, year = {2019} } @inproceedings{Wang2018ImprovingNL, author = {Xiaoyan Wang and Pavan Kapanipathi and Ryan Musa and Mo Yu and Kartik Talamadupula and Ibrahim Abdelaziz and Maria Chang and Achille Fokoue and Bassem Makni and Nicholas Mattei and Michael Witbrock}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/WangKMYTACFMMW19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33017208}, pages = {7208--7215}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {Improving Natural Language Inference Using External Knowledge in the Science Questions Domain}, url = {https://doi.org/10.1609/aaai.v33i01.33017208}, year = {2019} } @inproceedings{Wang2019ImprovingNL, author = {Xiaoyan Wang and Pavan Kapanipathi and Ryan Musa and Mo Yu and Kartik Talamadupula and Ibrahim Abdelaziz and Maria Chang and Achille Fokoue and Bassem Makni and Nicholas Mattei and Michael Witbrock}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/WangKMYTACFMMW19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33017208}, pages = {7208--7215}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {Improving Natural Language Inference Using External Knowledge in the Science Questions Domain}, url = {https://doi.org/10.1609/aaai.v33i01.33017208}, year = {2019} } @inproceedings{wang2019superglue, author = {Alex Wang and Yada Pruksachatkun and Nikita Nangia and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/WangPNSMHLB19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {3261--3275}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {SuperGLUE: {A} Stickier Benchmark for General-Purpose Language Understanding Systems}, url = {https://proceedings.neurips.cc/paper/2019/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html}, year = {2019} } @inproceedings{wang_2019_iccv, author = {Xin Wang and Jiawei Wu and Junkun Chen and Lei Li and Yuan{-}Fang Wang and William Yang Wang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/WangWCLWW19.bib}, booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2019, Seoul, Korea (South), October 27 - November 2, 2019}, doi = {10.1109/ICCV.2019.00468}, pages = {4580--4590}, publisher = {{IEEE}}, timestamp = {Wed, 09 Sep 2020 01:00:00 +0200}, title = {VaTeX: {A} Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research}, url = {https://doi.org/10.1109/ICCV.2019.00468}, year = {2019} } @article{weissenborn2017dynamic, author = {Weissenborn, Dirk and Ko{\v{c}}isk{\`y}, Tom{\'a}{\v{s}} and Dyer, Chris}, journal = {ArXiv preprint}, title = {Dynamic integration of background knowledge in neural NLU systems}, url = {https://arxiv.org/abs/1706.02596}, volume = {abs/1706.02596}, year = {2017} } @inproceedings{Weissenborn2018DynamicIO, author = {Dirk Weissenborn and Tom'avs Kovcisk'y and Chris Dyer}, title = {Dynamic Integration of Background Knowledge in Neural NLU Systems}, year = {2018} } @article{Wolf2019HuggingFacesTS, author = {Thomas Wolf and Lysandre Debut and Victor Sanh and Julien Chaumond and Clement Delangue and Anthony Moi and Pierric Cistac and Tim Rault and R'emi Louf and Morgan Funtowicz and Jamie Brew}, journal = {ArXiv preprint}, title = {HuggingFace's Transformers: State-of-the-art Natural Language Processing}, url = {https://arxiv.org/abs/1910.03771}, volume = {abs/1910.03771}, year = {2019} } @inproceedings{xu2018automaticeo, address = {Melbourne, Australia}, author = {Xu, Frank F. and Lin, Bill Yuchen and Zhu, Kenny}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, doi = {10.18653/v1/P18-2016}, pages = {96--101}, publisher = {Association for Computational Linguistics}, title = {Automatic Extraction of Commonsense {L}ocated{N}ear Knowledge}, url = {https://aclanthology.org/P18-2016}, year = {2018} } @inproceedings{yang2016hierarchicalan, address = {San Diego, California}, author = {Yang, Zichao and Yang, Diyi and Dyer, Chris and He, Xiaodong and Smola, Alex and Hovy, Eduard}, booktitle = {Proceedings of the 2016 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/N16-1174}, pages = {1480--1489}, publisher = {Association for Computational Linguistics}, title = {Hierarchical Attention Networks for Document Classification}, url = {https://aclanthology.org/N16-1174}, year = {2016} } @inproceedings{yang2017leveragingkb, address = {Vancouver, Canada}, author = {Yang, Bishan and Mitchell, Tom}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1132}, pages = {1436--1446}, publisher = {Association for Computational Linguistics}, title = {Leveraging Knowledge Bases in {LSTM}s for Improving Machine Reading}, url = {https://aclanthology.org/P17-1132}, year = {2017} } @inproceedings{yang2018hotpotqa, address = {Brussels, Belgium}, author = {Yang, Zhilin and Qi, Peng and Zhang, Saizheng and Bengio, Yoshua and Cohen, William and Salakhutdinov, Ruslan and Manning, Christopher D.}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1259}, pages = {2369--2380}, publisher = {Association for Computational Linguistics}, title = {{H}otpot{QA}: A Dataset for Diverse, Explainable Multi-hop Question Answering}, url = {https://aclanthology.org/D18-1259}, year = {2018} } @inproceedings{yang2019enhancingtg, address = {Florence, Italy}, author = {Yang, Pengcheng and Li, Lei and Luo, Fuli and Liu, Tianyu and Sun, Xu}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1193}, pages = {2002--2012}, publisher = {Association for Computational Linguistics}, title = {Enhancing Topic-to-Essay Generation with External Commonsense Knowledge}, url = {https://aclanthology.org/P19-1193}, year = {2019} } @inproceedings{yang2019knowledgeablesa, author = {Pengcheng Yang and Fuli Luo and Peng Chen and Lei Li and Zhiyi Yin and Xiaodong He and Xu Sun}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/YangLCLYHS19.bib}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, doi = {10.24963/ijcai.2019/744}, editor = {Sarit Kraus}, pages = {5356--5362}, publisher = {ijcai.org}, timestamp = {Wed, 02 Sep 2020 01:00:00 +0200}, title = {Knowledgeable Storyteller: {A} Commonsense-Driven Generative Model for Visual Storytelling}, url = {https://doi.org/10.24963/ijcai.2019/744}, year = {2019} } @inproceedings{yang2019xlnetga, author = {Zhilin Yang and Zihang Dai and Yiming Yang and Jaime G. Carbonell and Ruslan Salakhutdinov and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/YangDYCSL19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {5754--5764}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding}, url = {https://proceedings.neurips.cc/paper/2019/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html}, year = {2019} } @inproceedings{yao2019plan, author = {Lili Yao and Nanyun Peng and Ralph M. Weischedel and Kevin Knight and Dongyan Zhao and Rui Yan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/YaoPWK0Y19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33017378}, pages = {7378--7385}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {Plan-and-Write: Towards Better Automatic Storytelling}, url = {https://doi.org/10.1609/aaai.v33i01.33017378}, year = {2019} } @article{young-etal-2014-image, address = {Cambridge, MA}, author = {Young, Peter and Lai, Alice and Hodosh, Micah and Hockenmaier, Julia}, doi = {10.1162/tacl_a_00166}, journal = {Transactions of the Association for Computational Linguistics}, pages = {67--78}, publisher = {MIT Press}, title = {From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions}, url = {https://aclanthology.org/Q14-1006}, volume = {2}, year = {2014} } @inproceedings{zellers2018swagal, address = {Brussels, Belgium}, author = {Zellers, Rowan and Bisk, Yonatan and Schwartz, Roy and Choi, Yejin}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1009}, pages = {93--104}, publisher = {Association for Computational Linguistics}, title = {{SWAG}: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference}, url = {https://aclanthology.org/D18-1009}, year = {2018} } @inproceedings{zellers2019fromrt, author = {Rowan Zellers and Yonatan Bisk and Ali Farhadi and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/ZellersBFC19.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019}, doi = {10.1109/CVPR.2019.00688}, pages = {6720--6731}, publisher = {Computer Vision Foundation / {IEEE}}, timestamp = {Mon, 20 Jan 2020 00:00:00 +0100}, title = {From Recognition to Cognition: Visual Commonsense Reasoning}, url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Zellers\_From\_Recognition\_to\_Cognition\_Visual\_Commonsense\_Reasoning\_CVPR\_2019\_paper.html}, year = {2019} } @inproceedings{zellers2019hellaswagca, address = {Florence, Italy}, author = {Zellers, Rowan and Holtzman, Ari and Bisk, Yonatan and Farhadi, Ali and Choi, Yejin}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1472}, pages = {4791--4800}, publisher = {Association for Computational Linguistics}, title = {{H}ella{S}wag: Can a Machine Really Finish Your Sentence?}, url = {https://aclanthology.org/P19-1472}, year = {2019} } @article{zhang2015discriminativesw, address = {Cambridge, MA}, author = {Zhang, Yue and Clark, Stephen}, doi = {10.1162/COLI_a_00229}, journal = {Computational Linguistics}, number = {3}, pages = {503--538}, publisher = {MIT Press}, title = {Discriminative Syntax-Based Word Ordering for Text Generation}, url = {https://aclanthology.org/J15-3005}, volume = {41}, year = {2015} } @inproceedings{zhang2018graphco, address = {Brussels, Belgium}, author = {Zhang, Yuhao and Qi, Peng and Manning, Christopher D.}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1244}, pages = {2205--2215}, publisher = {Association for Computational Linguistics}, title = {Graph Convolution over Pruned Dependency Trees Improves Relation Extraction}, url = {https://aclanthology.org/D18-1244}, year = {2018} } @inproceedings{zhang2019conversationgw, address = {Online}, author = {Zhang, Houyu and Liu, Zhenghao and Xiong, Chenyan and Liu, Zhiyuan}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.184}, pages = {2031--2043}, publisher = {Association for Computational Linguistics}, title = {Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs}, url = {https://aclanthology.org/2020.acl-main.184}, year = {2020} } @inproceedings{zhang2020bertscore, author = {Tianyi Zhang and Varsha Kishore and Felix Wu and Kilian Q. Weinberger and Yoav Artzi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ZhangKWWA20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Wed, 03 Jun 2020 01:00:00 +0200}, title = {BERTScore: Evaluating Text Generation with {BERT}}, url = {https://openreview.net/forum?id=SkeHuCVFDr}, year = {2020} } @inproceedings{Zhang2020BERTScoreET, author = {Tianyi Zhang and Varsha Kishore and Felix Wu and Kilian Q. Weinberger and Yoav Artzi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ZhangKWWA20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Wed, 03 Jun 2020 01:00:00 +0200}, title = {BERTScore: Evaluating Text Generation with {BERT}}, url = {https://openreview.net/forum?id=SkeHuCVFDr}, year = {2020} } @article{Zhong2018ImprovingQA, author = {Wanjun Zhong and Duyu Tang and Nan Duan and Ming Zhou and Jiahai Wang and Jian Yin}, journal = {ArXiv preprint}, title = {Improving Question Answering by Commonsense-Based Pre-Training}, url = {https://arxiv.org/abs/1809.03568}, volume = {abs/1809.03568}, year = {2018} } @inproceedings{zhou2017emotionalcm, author = {Hao Zhou and Minlie Huang and Tianyang Zhang and Xiaoyan Zhu and Bing Liu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/ZhouHZZL18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {730--739}, publisher = {{AAAI} Press}, timestamp = {Wed, 08 Jan 2020 00:00:00 +0100}, title = {Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16455}, year = {2018} } @inproceedings{zhou2018commonsenseka, author = {Hao Zhou and Tom Young and Minlie Huang and Haizhou Zhao and Jingfang Xu and Xiaoyan Zhu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/ZhouYHZXZ18.bib}, booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm, Sweden}, doi = {10.24963/ijcai.2018/643}, editor = {J{\'{e}}r{\^{o}}me Lang}, pages = {4623--4629}, publisher = {ijcai.org}, timestamp = {Tue, 03 Sep 2019 01:00:00 +0200}, title = {Commonsense Knowledge Aware Conversation Generation with Graph Attention}, url = {https://doi.org/10.24963/ijcai.2018/643}, year = {2018} } @article{zhou2018graph, author = {Zhou, Jie and Cui, Ganqu and Zhang, Zhengyan and Yang, Cheng and Liu, Zhiyuan and Sun, Maosong}, journal = {ArXiv preprint}, title = {Graph Neural Networks: A Review of Methods and Applications}, url = {https://arxiv.org/abs/1812.08434}, volume = {abs/1812.08434}, year = {2018} } @article{Zhu2019TextI, author = {Wanrong Zhu and Zhiting Hu and Eric P. Xing}, journal = {ArXiv preprint}, title = {Text Infilling}, url = {https://arxiv.org/abs/1901.00158}, volume = {abs/1901.00158}, year = {2019} } @inproceedings{NEURIPS2019_f4dd765c, author = {Khurram Javed and Martha White}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/JavedW19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {1818--1828}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Meta-Learning Representations for Continual Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/f4dd765c12f2ef67f98f3558c282a9cd-Abstract.html}, year = {2019} } @article{french1999catastrophic, author = {French, Robert M}, journal = {Trends in cognitive sciences}, number = {4}, pages = {128--135}, publisher = {Elsevier}, title = {Catastrophic forgetting in connectionist networks}, volume = {3}, year = {1999} } @inproceedings{sun2019lamol, author = {Fan{-}Keng Sun and Cheng{-}Hao Ho and Hung{-}Yi Lee}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/SunHL20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{LAMOL:} LAnguage MOdeling for Lifelong Language Learning}, url = {https://openreview.net/forum?id=Skgxcn4YDS}, year = {2020} } @inproceedings{wang2019glue, author = {Alex Wang and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/WangSMHLB19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {{GLUE:} {A} Multi-Task Benchmark and Analysis Platform for Natural Language Understanding}, url = {https://openreview.net/forum?id=rJ4km2R5t7}, year = {2019} } @inproceedings{sun2019fine, author = {Sun, Chi and Qiu, Xipeng and Xu, Yige and Huang, Xuanjing}, booktitle = {China National Conference on Chinese Computational Linguistics}, organization = {Springer}, pages = {194--206}, title = {How to fine-tune BERT for text classification?}, year = {2019} } @inproceedings{xu2019bert, address = {Minneapolis, Minnesota}, author = {Xu, Hu and Liu, Bing and Shu, Lei and Yu, Philip}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1242}, pages = {2324--2335}, publisher = {Association for Computational Linguistics}, title = {{BERT} Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis}, url = {https://aclanthology.org/N19-1242}, year = {2019} } @inproceedings{widmer1993effective, author = {Widmer, Gerhard and Kubat, Miroslav}, booktitle = {European Conference on Machine Learning}, organization = {Springer}, pages = {227--243}, title = {Effective learning in dynamic environments by explicit context tracking}, year = {1993} } @inproceedings{biesialska2020continual, address = {Barcelona, Spain (Online)}, author = {Biesialska, Magdalena and Biesialska, Katarzyna and Costa-juss{\`a}, Marta R.}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, doi = {10.18653/v1/2020.coling-main.574}, pages = {6523--6541}, publisher = {International Committee on Computational Linguistics}, title = {Continual Lifelong Learning in Natural Language Processing: A Survey}, url = {https://aclanthology.org/2020.coling-main.574}, year = {2020} } @inproceedings{sun2019utilizing, address = {Minneapolis, Minnesota}, author = {Sun, Chi and Huang, Luyao and Qiu, Xipeng}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1035}, pages = {380--385}, publisher = {Association for Computational Linguistics}, title = {Utilizing {BERT} for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence}, url = {https://aclanthology.org/N19-1035}, year = {2019} } @inproceedings{NEURIPS2019_4496bf24, author = {Alex Wang and Yada Pruksachatkun and Nikita Nangia and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/WangPNSMHLB19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {3261--3275}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {SuperGLUE: {A} Stickier Benchmark for General-Purpose Language Understanding Systems}, url = {https://proceedings.neurips.cc/paper/2019/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html}, year = {2019} } @inproceedings{yang2019xlnet, author = {Zhilin Yang and Zihang Dai and Yiming Yang and Jaime G. Carbonell and Ruslan Salakhutdinov and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/YangDYCSL19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {5754--5764}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding}, url = {https://proceedings.neurips.cc/paper/2019/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html}, year = {2019} } @inproceedings{linzen2020can, address = {Online}, author = {Linzen, Tal}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.465}, pages = {5210--5217}, publisher = {Association for Computational Linguistics}, title = {How Can We Accelerate Progress Towards Human-like Linguistic Generalization?}, url = {https://aclanthology.org/2020.acl-main.465}, year = {2020} } @inproceedings{devlin2018bert, address = {Minneapolis, Minnesota}, author = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1423}, pages = {4171--4186}, publisher = {Association for Computational Linguistics}, title = {{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding}, url = {https://aclanthology.org/N19-1423}, year = {2019} } @inproceedings{Requeima2019FastAF, author = {James Requeima and Jonathan Gordon and John Bronskill and Sebastian Nowozin and Richard E. Turner}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/Requeima0BNT19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {7957--7968}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes}, url = {https://proceedings.neurips.cc/paper/2019/hash/1138d90ef0a0848a542e57d1595f58ea-Abstract.html}, year = {2019} } @inproceedings{zintgraf2019fast, author = {Luisa M. Zintgraf and Kyriacos Shiarlis and Vitaly Kurin and Katja Hofmann and Shimon Whiteson}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/ZintgrafSKHW19.bib}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, pages = {7693--7702}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 11 Jun 2019 01:00:00 +0200}, title = {Fast Context Adaptation via Meta-Learning}, url = {http://proceedings.mlr.press/v97/zintgraf19a.html}, volume = {97}, year = {2019} } @phdthesis{schmidhuber1987evolutionary, author = {Schmidhuber, J{\""u}rgen}, school = {Technische Universit{\""a}t M{\""u}nchen}, title = {Evolutionary principles in self-referential learning, or on learning how to learn: the meta-meta-... hook}, year = {1987} } @inproceedings{finn2017model, author = {Chelsea Finn and Pieter Abbeel and Sergey Levine}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/FinnAL17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {1126--1135}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks}, url = {http://proceedings.mlr.press/v70/finn17a.html}, volume = {70}, year = {2017} } @inproceedings{Oswald2020ContinualLW, author = {Johannes von Oswald and Christian Henning and Jo{\~{a}}o Sacramento and Benjamin F. Grewe}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/OswaldHSG20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Continual learning with hypernetworks}, url = {https://openreview.net/forum?id=SJgwNerKvB}, year = {2020} } @article{Ye2021ZeroshotLB, author = {Qinyuan Ye and X. Ren}, journal = {ArXiv preprint}, title = {Zero-shot Learning by Generating Task-specific Adapters}, url = {https://arxiv.org/abs/2101.00420}, volume = {abs/2101.00420}, year = {2021} } @article{He2019TaskAC, author = {X. He and Jakub Sygnowski and Alexandre Galashov and Andrei A. Rusu and Y. Teh and Razvan Pascanu}, journal = {ArXiv preprint}, title = {Task Agnostic Continual Learning via Meta Learning}, url = {https://arxiv.org/abs/1906.05201}, volume = {abs/1906.05201}, year = {2019} } @inproceedings{Rajasegaran2020iTAMLAI, author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/RajasegaranKHKS20.bib}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, doi = {10.1109/CVPR42600.2020.01360}, pages = {13585--13594}, publisher = {{IEEE}}, timestamp = {Tue, 11 Aug 2020 01:00:00 +0200}, title = {iTAML: An Incremental Task-Agnostic Meta-learning Approach}, url = {https://doi.org/10.1109/CVPR42600.2020.01360}, year = {2020} } @inproceedings{Chuang2020LifelongLK, address = {Online}, author = {Chuang, Yung-Sung and Su, Shang-Yu and Chen, Yun-Nung}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.233}, pages = {2914--2924}, publisher = {Association for Computational Linguistics}, title = {Lifelong Language Knowledge Distillation}, url = {https://aclanthology.org/2020.emnlp-main.233}, year = {2020} } @inproceedings{Sun2020LAMOLLM, author = {Fan{-}Keng Sun and Cheng{-}Hao Ho and Hung{-}Yi Lee}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/SunHL20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{LAMOL:} LAnguage MOdeling for Lifelong Language Learning}, url = {https://openreview.net/forum?id=Skgxcn4YDS}, year = {2020} } @inproceedings{Wang2020EfficientML, address = {Online}, author = {Wang, Zirui and Mehta, Sanket Vaibhav and Poczos, Barnabas and Carbonell, Jaime}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.39}, pages = {535--548}, publisher = {Association for Computational Linguistics}, title = {Efficient Meta Lifelong-Learning with Limited Memory}, url = {https://aclanthology.org/2020.emnlp-main.39}, year = {2020} } @inproceedings{Riemer2019LearningTL, author = {Matthew Riemer and Ignacio Cases and Robert Ajemian and Miao Liu and Irina Rish and Yuhai Tu and Gerald Tesauro}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/RiemerCALRTT19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 12 Sep 2019 01:00:00 +0200}, title = {Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference}, url = {https://openreview.net/forum?id=B1gTShAct7}, year = {2019} } @inproceedings{Jerfel2019ReconcilingMA, author = {Ghassen Jerfel and Erin Grant and Tom Griffiths and Katherine A. Heller}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/JerfelGGH19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {9119--9130}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Reconciling meta-learning and continual learning with online mixtures of tasks}, url = {https://proceedings.neurips.cc/paper/2019/hash/7a9a322cbe0d06a98667fdc5160dc6f8-Abstract.html}, year = {2019} } @inproceedings{Pfeiffer2020AdapterFusionNT, address = {Online}, author = {Pfeiffer, Jonas and Kamath, Aishwarya and R{\""u}ckl{\'e}, Andreas and Cho, Kyunghyun and Gurevych, Iryna}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, doi = {10.18653/v1/2021.eacl-main.39}, pages = {487--503}, publisher = {Association for Computational Linguistics}, title = {{A}dapter{F}usion: Non-Destructive Task Composition for Transfer Learning}, url = {https://aclanthology.org/2021.eacl-main.39}, year = {2021} } @article{robins1995catastrophic, author = {Robins, Anthony}, journal = {Connection Science}, number = {2}, pages = {123--146}, publisher = {Citeseer}, title = {Catastrophic forgetting, rehearsal and pseudorehearsal}, volume = {7}, year = {1995} } @article{gama2014survey, author = {Gama, Jo{\~a}o and {\v{Z}}liobait{\.e}, Indr{\.e} and Bifet, Albert and Pechenizkiy, Mykola and Bouchachia, Abdelhamid}, journal = {CSUR}, number = {4}, pages = {1--37}, publisher = {ACM New York, NY, USA}, title = {A survey on concept drift adaptation}, volume = {46}, year = {2014} } @article{morgenstern2014properties, author = {Morgenstern, Yaniv and Rostami, Mohammad and Purves, Dale}, journal = {Proceedings of the National Academy of Sciences}, number = {Supplement 3}, pages = {10868--10872}, publisher = {National Acad Sciences}, title = {Properties of artificial networks evolved to contend with natural spectra}, volume = {111}, year = {2014} } @article{bolley2007quantitative, author = {Bolley, Fran{\c{c}}ois and Guillin, Arnaud and Villani, C{\'e}dric}, journal = {Probability Theory and Related Fields}, number = {3-4}, pages = {541--593}, publisher = {Springer}, title = {Quantitative concentration inequalities for empirical measures on non-compact spaces}, volume = {137}, year = {2007} } @book{saitoh1997integral, author = {Saitoh, Saburou}, publisher = {CRC Press}, title = {Integral transforms, reproducing kernels and their applications}, volume = {369}, year = {1997} } @article{diek2010, author = {Diekelmann, Susanne and Born, Jan}, journal = {Nature Reviews Neuroscience}, number = {2}, pages = {114}, publisher = {Nature Publishing Group}, title = {The memory function of sleep}, volume = {11}, year = {2010} } @article{rasch2013, author = {Rasch, Bj{\""o}rn and Born, Jan}, journal = {Physiological Reviews}, number = {2}, pages = {681--766}, publisher = {American Physiological Society Bethesda, MD}, title = {About sleep's role in memory}, volume = {93}, year = {2013} } @inproceedings{shin2017continual, author = {Hanul Shin and Jung Kwon Lee and Jaehong Kim and Jiwon Kim}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ShinLKK17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {2990--2999}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Continual Learning with Deep Generative Replay}, url = {https://proceedings.neurips.cc/paper/2017/hash/0efbe98067c6c73dba1250d2beaa81f9-Abstract.html}, year = {2017} } @article{li2018learning, author = {Li, Zhizhong and Hoiem, Derek}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {12}, pages = {2935--2947}, publisher = {IEEE}, title = {Learning without forgetting}, volume = {40}, year = {2018} } @inproceedings{metz2016unrolled, author = {Luke Metz and Ben Poole and David Pfau and Jascha Sohl{-}Dickstein}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/MetzPPS17.bib}, booktitle = {5th International Conference on Learning Representations, {ICLR} 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Unrolled Generative Adversarial Networks}, url = {https://openreview.net/forum?id=BydrOIcle}, year = {2017} } @inproceedings{krizhevsky2012imagenet, author = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/KrizhevskySH12.bib}, booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States}, editor = {Peter L. Bartlett and Fernando C. N. Pereira and Christopher J. C. Burges and L{\'{e}}on Bottou and Kilian Q. Weinberger}, pages = {1106--1114}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {ImageNet Classification with Deep Convolutional Neural Networks}, url = {https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html}, year = {2012} } @inproceedings{rabin2011wasserstein, author = {Rabin, Julien and Peyr{\'e}, Gabriel}, booktitle = {2011 18th IEEE International Conference on Image Processing}, organization = {IEEE}, pages = {1541--1544}, title = {Wasserstein regularization of imaging problem}, year = {2011} } @inproceedings{redko2017theoretical, author = {Redko, Ievgen and Habrard, Amaury and Sebban, Marc}, booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases}, organization = {Springer}, pages = {737--753}, title = {Theoretical analysis of domain adaptation with optimal transport}, year = {2017} } @misc{WinNT, author = {Ryuichiro Hataya}, howpublished = {\url{https://github.com/moskomule/ewc.pytorch}}, note = {[Online; accessed 14-June-2019]}, title = {{EWC} {P}y{T}orch}, year = {2019} } @article{mcinnes2018umap, author = {McInnes, Leland and Healy, John and Melville, James}, journal = {ArXiv preprint}, title = {UMAP: Uniform manifold approximation and projection for dimension reduction}, url = {https://arxiv.org/abs/1802.03426}, volume = {abs/1802.03426}, year = {2018} } @article{courty2017optimal, author = {Courty, Nicolas and Flamary, R{\'e}mi and Tuia, Devis and Rakotomamonjy, Alain}, journal = {IEEE TPAMI}, number = {9}, pages = {1853--1865}, publisher = {IEEE}, title = {Optimal transport for domain adaptation}, volume = {39}, year = {2017} } @phdthesis{bonnotte2013unidimensional, author = {Bonnotte, Nicolas}, school = {Paris 11}, title = {Unidimensional and evolution methods for optimal transportation}, year = {2013} } @article{chen2016lifelong, author = {Chen, Zhiyuan and Liu, Bing}, journal = {Synthesis Lectures on Artificial Intelligence and Machine Learning}, number = {3}, pages = {1--145}, publisher = {Morgan \& Claypool Publishers}, title = {Lifelong machine learning}, volume = {10}, year = {2016} } @book{chomsky2002syntactic, author = {Chomsky, Noam}, publisher = {Walter de Gruyter}, title = {Syntactic structures}, year = {2002} } @book{shalev2014understanding, author = {Shalev-Shwartz, Shai and Ben-David, Shai}, publisher = {Cambridge University Press}, title = {Understanding machine learning: From theory to algorithms}, year = {2014} } @inproceedings{srivastava2017veegan, author = {Akash Srivastava and Lazar Valkov and Chris Russell and Michael U. Gutmann and Charles Sutton}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SrivastavaVRGS17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {3308--3318}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {{VEEGAN:} Reducing Mode Collapse in GANs using Implicit Variational Learning}, url = {https://proceedings.neurips.cc/paper/2017/hash/44a2e0804995faf8d2e3b084a1e2db1d-Abstract.html}, year = {2017} } @inproceedings{roth2017stabilizing, author = {Kevin Roth and Aur{\'{e}}lien Lucchi and Sebastian Nowozin and Thomas Hofmann}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/RothLNH17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {2018--2028}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Stabilizing Training of Generative Adversarial Networks through Regularization}, url = {https://proceedings.neurips.cc/paper/2017/hash/7bccfde7714a1ebadf06c5f4cea752c1-Abstract.html}, year = {2017} } @article{mcclelland1995there, author = {McClelland, James L and McNaughton, Bruce L and O'Reilly, Randall C}, journal = {Psychological Review}, number = {3}, pages = {419}, publisher = {American Psychological Association}, title = {Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory.}, volume = {102}, year = {1995} } @article{widmer1996learning, author = {Widmer, Gerhard and Kubat, Miroslav}, journal = {Machine learning}, number = {1}, pages = {69--101}, publisher = {Springer}, title = {Learning in the presence of concept drift and hidden contexts}, volume = {23}, year = {1996} } @article{gennari1989models, author = {Gennari, John H and Langley, Pat and Fisher, Doug}, journal = {Artificial intelligence}, number = {1-3}, pages = {11--61}, publisher = {Elsevier}, title = {Models of incremental concept formation}, volume = {40}, year = {1989} } @inproceedings{french1991using, author = {French, Robert M}, booktitle = {Proceedings of the 13th annual cognitive science society conference}, pages = {173--178}, title = {Using semi-distributed representations to overcome catastrophic forgetting in connectionist networks}, volume = {1}, year = {1991} } @article{gelbard2008internally, author = {Gelbard-Sagiv, Hagar and Mukamel, Roy and Harel, Michal and Malach, Rafael and Fried, Itzhak}, journal = {Science}, number = {5898}, pages = {96--101}, publisher = {American Association for the Advancement of Science}, title = {Internally generated reactivation of single neurons in human hippocampus during free recall}, volume = {322}, year = {2008} } @inproceedings{kolouri2018sliced, author = {Soheil Kolouri and Gustavo K. Rohde and Heiko Hoffmann}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/KolouriRH18.bib}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, doi = {10.1109/CVPR.2018.00361}, pages = {3427--3436}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 27 Mar 2020 00:00:00 +0100}, title = {Sliced Wasserstein Distance for Learning Gaussian Mixture Models}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Kolouri\_Sliced\_Wasserstein\_Distance\_CVPR\_2018\_paper.html}, year = {2018} } @article{ans1997avoiding, author = {Ans, Bernard and Rousset, St{\'e}phane}, journal = {Comptes Rendus de l'Acad{\'e}mie des Sciences-Series III-Sciences de la Vie}, number = {12}, pages = {989--997}, publisher = {Elsevier}, title = {Avoiding catastrophic forgetting by coupling two reverberating neural networks}, volume = {320}, year = {1997} } @article{hattori2014biologically, author = {Hattori, Motonobu}, journal = {Neurocomputing}, pages = {262--268}, publisher = {Elsevier}, title = {A biologically inspired dual-network memory model for reduction of catastrophic forgetting}, volume = {134}, year = {2014} } @inproceedings{zenke2017continual, author = {Friedemann Zenke and Ben Poole and Surya Ganguli}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/ZenkePG17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {3987--3995}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Continual Learning Through Synaptic Intelligence}, url = {http://proceedings.mlr.press/v70/zenke17a.html}, volume = {70}, year = {2017} } @article{lamprecht2004structural, author = {Lamprecht, Raphael and LeDoux, Joseph}, journal = {Nature Reviews Neuroscience}, number = {1}, pages = {45}, publisher = {Nature Publishing Group}, title = {Structural plasticity and memory}, volume = {5}, year = {2004} } @inproceedings{aljundi2018memory, author = {Aljundi, Rahaf and Babiloni, Francesca and Elhoseiny, Mohamed and Rohrbach, Marcus and Tuytelaars, Tinne}, booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)}, pages = {139--154}, title = {Memory aware synapses: Learning what (not) to forget}, year = {2018} } @inproceedings{isele2018selective, author = {David Isele and Akansel Cosgun}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/IseleC18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {3302--3309}, publisher = {{AAAI} Press}, timestamp = {Mon, 22 Oct 2018 01:00:00 +0200}, title = {Selective Experience Replay for Lifelong Learning}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16054}, year = {2018} } @inproceedings{schaul2015prioritized, author = {Tom Schaul and John Quan and Ioannis Antonoglou and David Silver}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/journals/corr/SchaulQAS15.bib}, booktitle = {4th International Conference on Learning Representations, {ICLR} 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings}, editor = {Yoshua Bengio and Yann LeCun}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Prioritized Experience Replay}, url = {http://arxiv.org/abs/1511.05952}, year = {2016} } @inproceedings{jiang1997semantic, address = {Taipei, Taiwan}, author = {Jiang, Jay J. and Conrath, David W.}, booktitle = {Proceedings of the 10th Research on Computational Linguistics International Conference}, pages = {19--33}, publisher = {The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)}, title = {Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy}, url = {https://aclanthology.org/O97-1002}, year = {1997} } @inproceedings{goodfellow2014generative, author = {Ian J. Goodfellow and Jean Pouget{-}Abadie and Mehdi Mirza and Bing Xu and David Warde{-}Farley and Sherjil Ozair and Aaron C. Courville and Yoshua Bengio}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/GoodfellowPMXWOCB14.bib}, booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada}, editor = {Zoubin Ghahramani and Max Welling and Corinna Cortes and Neil D. Lawrence and Kilian Q. Weinberger}, pages = {2672--2680}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Generative Adversarial Nets}, url = {https://proceedings.neurips.cc/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html}, year = {2014} } @inproceedings{petroni2020kilt, address = {Online}, author = {Petroni, Fabio and Piktus, Aleksandra and Fan, Angela and Lewis, Patrick and Yazdani, Majid and De Cao, Nicola and Thorne, James and Jernite, Yacine and Karpukhin, Vladimir and Maillard, Jean and Plachouras, Vassilis and Rockt{\""a}schel, Tim and Riedel, Sebastian}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.200}, pages = {2523--2544}, publisher = {Association for Computational Linguistics}, title = {{KILT}: a Benchmark for Knowledge Intensive Language Tasks}, url = {https://aclanthology.org/2021.naacl-main.200}, year = {2021} } @book{grossberg2012studies, author = {Grossberg, Stephen T}, publisher = {Springer Science \& Business Media}, title = {Studies of mind and brain: Neural principles of learning, perception, development, cognition, and motor control}, volume = {70}, year = {2012} } @article{kirkpatrick2017overcoming, author = {Kirkpatrick, James and Pascanu, Razvan and Rabinowitz, Neil and Others}, journal = {Proceedings of the national academy of sciences}, number = {13}, pages = {3521--3526}, publisher = {National Acad Sciences}, title = {Overcoming catastrophic forgetting in neural networks}, volume = {114}, year = {2017} } @inproceedings{lecun1990handwritten, author = {LeCun, Yann and Boser, Bernhard and Denker, John and Others}, booktitle = {Advances in Neural Information Processing Systems}, pages = {396--404}, title = {Handwritten digit recognition with a back-propagation network}, year = {1990} } @article{song2000competitive, author = {Song, Sen and Miller, Kenneth D and Abbott, Larry F}, journal = {Nature neuroscience}, number = {9}, pages = {919--926}, title = {Competitive Hebbian learning through spike-timing-dependent synaptic plasticity}, volume = {3}, year = {2000} } @article{hinton1984distributed, author = {Hinton, Geoffrey E and McClelland, James L and Rumelhart, David E}, publisher = {Carnegie Mellon University}, title = {Distributed representations}, year = {1984} } @article{hasson2020direct, author = {Hasson, Uri and Nastase, Samuel A and Goldstein, Ariel}, journal = {Neuron}, number = {3}, pages = {416--434}, publisher = {Elsevier}, title = {Direct fit to nature: An evolutionary perspective on biological and artificial neural networks}, volume = {105}, year = {2020} } @inproceedings{heinen2012using, author = {Heinen, Milton Roberto and Engel, Paulo Martins and Pinto, Rafael C}, booktitle = {The 2012 International Joint Conference on Neural Networks (IJCNN)}, organization = {IEEE}, pages = {1--8}, title = {Using a Gaussian mixture neural network for incremental learning and robotics}, year = {2012} } @article{mcclelland1986parallel, author = {McClelland, James L and Rumelhart, David E and PDP Research Group and others}, journal = {Explorations in the Microstructure of Cognition}, pages = {216--271}, publisher = {MIT Press Cambridge, Ma}, title = {Parallel distributed processing}, volume = {2}, year = {1986} } @inproceedings{rannen2017encoder, author = {Amal Rannen Triki and Rahaf Aljundi and Matthew B. Blaschko and Tinne Tuytelaars}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/TrikiABT17.bib}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2017, Venice, Italy, October 22-29, 2017}, doi = {10.1109/ICCV.2017.148}, pages = {1329--1337}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 27 Dec 2019 00:00:00 +0100}, title = {Encoder Based Lifelong Learning}, url = {https://doi.org/10.1109/ICCV.2017.148}, year = {2017} } @article{mcclelland2003parallel, author = {McClelland, James L and Rogers, Timothy T}, journal = {Nature reviews Neuro.}, number = {4}, pages = {310--322}, title = {The parallel distributed processing approach to semantic cognition}, volume = {4}, year = {2003} } @article{lake2015human, author = {Lake, Brenden M and Salakhutdinov, Ruslan and Tenenbaum, Joshua B}, journal = {Science}, number = {6266}, pages = {1332--1338}, publisher = {American Association for the Advancement of Science}, title = {Human-level concept learning through probabilistic program induction}, volume = {350}, year = {2015} } @article{parisi2019continual, author = {Parisi, German I and Kemker, Ronald and Part, Jose L and Kanan, Christopher and Wermter, Stefan}, journal = {Neural Networks}, publisher = {Elsevier}, title = {Continual lifelong learning with neural networks: A review}, year = {2019} } @inproceedings{snell2017prototypical, author = {Jake Snell and Kevin Swersky and Richard S. Zemel}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SnellSZ17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {4077--4087}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Prototypical Networks for Few-shot Learning}, url = {https://proceedings.neurips.cc/paper/2017/hash/cb8da6767461f2812ae4290eac7cbc42-Abstract.html}, year = {2017} } @article{arjovsky2017wasserstein, author = {Arjovsky, Martin and Chintala, Soumith and Bottou, L{\'e}on}, journal = {ArXiv preprint}, title = {Wasserstein gan}, url = {https://arxiv.org/abs/1701.07875}, volume = {abs/1701.07875}, year = {2017} } @article{bonneel2015sliced, author = {Bonneel, Nicolas and Rabin, Julien and Peyr{\'e}, Gabriel and Pfister, Hanspeter}, journal = {Journal of Math. Imag. and Vision}, number = {1}, pages = {22--45}, publisher = {Springer}, title = {Sliced and radon wasserstein barycenters of measures}, volume = {51}, year = {2015} } @inproceedings{ashtiani2018nearly, author = {Hassan Ashtiani and Shai Ben{-}David and Nicholas J. A. Harvey and Christopher Liaw and Abbas Mehrabian and Yaniv Plan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/AshtianiBHLMP18.bib}, booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr{\'{e}}al, Canada}, editor = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicol{\`{o}} Cesa{-}Bianchi and Roman Garnett}, pages = {3416--3425}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes}, url = {https://proceedings.neurips.cc/paper/2018/hash/70ece1e1e0931919438fcfc6bd5f199c-Abstract.html}, year = {2018} } @inproceedings{globerson2006metric, author = {Amir Globerson and Sam T. Roweis}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/GlobersonR05.bib}, booktitle = {Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, {NIPS} 2005, December 5-8, 2005, Vancouver, British Columbia, Canada]}, pages = {451--458}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Metric Learning by Collapsing Classes}, url = {https://proceedings.neurips.cc/paper/2005/hash/ad8e88c0f76fa4fc8e5474384142a00a-Abstract.html}, year = {2005} } @article{mangal2007analysis, author = {Mangal, Manish and Singh, Manu Pratap}, journal = {International Journal on Artificial Intelligence Tools}, number = {01}, pages = {111--120}, publisher = {World Scientific}, title = {Analysis of multidimensional XOR classification problem with evolutionary feedforward neural networks}, volume = {16}, year = {2007} } @incollection{mccloskey1989catastrophic, author = {McCloskey, Michael and Cohen, Neal J}, booktitle = {Psychology of learning and motivation}, pages = {109--165}, publisher = {Elsevier}, title = {Catastrophic interference in connectionist networks: The sequential learning problem}, volume = {24}, year = {1989} } @article{saxe2019mathematical, author = {Saxe, Andrew M and McClelland, James L and Ganguli, Surya}, journal = {Proceedings of the National Academy of Sciences}, pages = {201820226}, publisher = {National Acad Sciences}, title = {A mathematical theory of semantic development in deep neural networks}, year = {2019} } @article{longcamp2005influence, author = {Longcamp, Marieke and Zerbato-Poudou, Marie-Th{\'e}r{\`e}se and Velay, Jean-Luc}, journal = {Acta psychologica}, number = {1}, pages = {67--79}, publisher = {Elsevier}, title = {The influence of writing practice on letter recognition in preschool children: A comparison between handwriting and typing}, volume = {119}, year = {2005} } @inproceedings{rostami2019Complementary, author = {Mohammad Rostami and Soheil Kolouri and Praveen K. Pilly}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/RostamiKP19.bib}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, doi = {10.24963/ijcai.2019/463}, editor = {Sarit Kraus}, pages = {3339--3345}, publisher = {ijcai.org}, timestamp = {Tue, 20 Aug 2019 01:00:00 +0200}, title = {Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay}, url = {https://doi.org/10.24963/ijcai.2019/463}, year = {2019} } @inproceedings{rebuffi2017icarl, author = {Sylvestre{-}Alvise Rebuffi and Alexander Kolesnikov and Georg Sperl and Christoph H. Lampert}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/RebuffiKSL17.bib}, booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2017, Honolulu, HI, USA, July 21-26, 2017}, doi = {10.1109/CVPR.2017.587}, pages = {5533--5542}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 20 Nov 2020 00:00:00 +0100}, title = {iCaRL: Incremental Classifier and Representation Learning}, url = {https://doi.org/10.1109/CVPR.2017.587}, year = {2017} } @inproceedings{kemker2017fearnet, author = {Ronald Kemker and Christopher Kanan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/KemkerK18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {FearNet: Brain-Inspired Model for Incremental Learning}, url = {https://openreview.net/forum?id=SJ1Xmf-Rb}, year = {2018} } @inproceedings{castro2018end, author = {Castro, Francisco M and Mar{\'\i}n-Jim{\'e}nez, Manuel J and Guil, Nicol{\'a}s and Schmid, Cordelia and Alahari, Karteek}, booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)}, pages = {233--248}, title = {End-to-end incremental learning}, year = {2018} } @article{hinton2015distilling, author = {Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff}, journal = {ArXiv preprint}, title = {Distilling the knowledge in a neural network}, url = {https://arxiv.org/abs/1503.02531}, volume = {abs/1503.02531}, year = {2015} } @article{roy2020tree, author = {Roy, Deboleena and Panda, Priyadarshini and Roy, Kaushik}, journal = {Neural Networks}, pages = {148--160}, publisher = {Elsevier}, title = {Tree-CNN: a hierarchical deep CNN for incremental learning}, volume = {121}, year = {2020} } @article{sarwar2019incremental, author = {Sarwar, Syed Shakib and Ankit, Aayush and Roy, Kaushik}, journal = {IEEE Access}, publisher = {IEEE}, title = {Incremental learning in deep convolutional neural networks using partial network sharing}, year = {2019} } @article{li2017learning, author = {Li, Zhizhong and Hoiem, Derek}, journal = {IEEE transactions on pattern analysis and machine intelligence}, number = {12}, pages = {2935--2947}, publisher = {IEEE}, title = {Learning without forgetting}, volume = {40}, year = {2017} } @inproceedings{javed2018revisiting, author = {Javed, Khurram and Shafait, Faisal}, booktitle = {Asian Conference on Computer Vision}, organization = {Springer}, pages = {3--17}, title = {Revisiting distillation and incremental classifier learning}, year = {2018} } @inproceedings{he2018overcoming, author = {Xu He and Herbert Jaeger}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/HeJ18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation}, url = {https://openreview.net/forum?id=B1al7jg0b}, year = {2018} } @inproceedings{lee2017overcoming, author = {Sang{-}Woo Lee and Jin{-}Hwa Kim and Jaehyun Jun and Jung{-}Woo Ha and Byoung{-}Tak Zhang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/LeeKJHZ17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {4652--4662}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Overcoming Catastrophic Forgetting by Incremental Moment Matching}, url = {https://proceedings.neurips.cc/paper/2017/hash/f708f064faaf32a43e4d3c784e6af9ea-Abstract.html}, year = {2017} } @inproceedings{wu2018memory, author = {Chenshen Wu and Luis Herranz and Xialei Liu and Yaxing Wang and Joost van de Weijer and Bogdan Raducanu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/WuHLWWR18.bib}, booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr{\'{e}}al, Canada}, editor = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicol{\`{o}} Cesa{-}Bianchi and Roman Garnett}, pages = {5966--5976}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Memory Replay GANs: Learning to Generate New Categories without Forgetting}, url = {https://proceedings.neurips.cc/paper/2018/hash/a57e8915461b83adefb011530b711704-Abstract.html}, year = {2018} } @article{zeng2019continual, author = {Zeng, Guanxiong and Chen, Yang and Cui, Bo and Yu, Shan}, journal = {Nature Machine Intelligence}, number = {8}, pages = {364--372}, publisher = {Nature Publishing Group}, title = {Continual learning of context-dependent processing in neural networks}, volume = {1}, year = {2019} } @inproceedings{aljundi2019gradient, author = {Rahaf Aljundi and Min Lin and Baptiste Goujaud and Yoshua Bengio}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/AljundiLGB19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {11816--11825}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Gradient based sample selection for online continual learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/e562cd9c0768d5464b64cf61da7fc6bb-Abstract.html}, year = {2019} } @inproceedings{lopez2017gradient, author = {David Lopez{-}Paz and Marc'Aurelio Ranzato}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/Lopez-PazR17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {6467--6476}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Gradient Episodic Memory for Continual Learning}, url = {https://proceedings.neurips.cc/paper/2017/hash/f87522788a2be2d171666752f97ddebb-Abstract.html}, year = {2017} } @article{zenke2017temporal, author = {Zenke, Friedemann and Gerstner, Wulfram and Ganguli, Surya}, journal = {Curr. opinion in neuro.}, pages = {166--176}, publisher = {Elsevier}, title = {The temporal paradox of Hebbian learning and homeostatic plasticity}, volume = {43}, year = {2017} } @article{van2020brain, author = {van de Ven, Gido M and Siegelmann, Hava T and Tolias, Andreas S}, journal = {Nature communications}, number = {1}, pages = {1--14}, publisher = {Nature Publishing Group}, title = {Brain-inspired replay for continual learning with artificial neural networks}, volume = {11}, year = {2020} } @inproceedings{vajjala-lucic-2018-onestopenglish, address = {New Orleans, Louisiana}, author = {Vajjala, Sowmya and Lu{\v{c}}i{\'c}, Ivana}, booktitle = {Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications}, doi = {10.18653/v1/W18-0535}, pages = {297--304}, publisher = {Association for Computational Linguistics}, title = {{O}ne{S}top{E}nglish corpus: A new corpus for automatic readability assessment and text simplification}, url = {https://aclanthology.org/W18-0535}, year = {2018} } @inproceedings{pang-lee-2005-seeing, address = {Ann Arbor, Michigan}, author = {Pang, Bo and Lee, Lillian}, booktitle = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics ({ACL}{'}05)}, doi = {10.3115/1219840.1219855}, pages = {115--124}, publisher = {Association for Computational Linguistics}, title = {Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales}, url = {https://aclanthology.org/P05-1015}, year = {2005} } @inproceedings{cohan-etal-2019-structural, address = {Minneapolis, Minnesota}, author = {Cohan, Arman and Ammar, Waleed and van Zuylen, Madeleine and Cady, Field}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1361}, pages = {3586--3596}, publisher = {Association for Computational Linguistics}, title = {Structural Scaffolds for Citation Intent Classification in Scientific Publications}, url = {https://aclanthology.org/N19-1361}, year = {2019} } @inproceedings{marelli-etal-2014-sick, address = {Reykjavik, Iceland}, author = {Marelli, Marco and Menini, Stefano and Baroni, Marco and Bentivogli, Luisa and Bernardi, Raffaella and Zamparelli, Roberto}, booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)}, pages = {216--223}, publisher = {European Language Resources Association (ELRA)}, title = {A {SICK} cure for the evaluation of compositional distributional semantic models}, url = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/363_Paper.pdf}, year = {2014} } @article{montague1970universal, author = {Montague, Richard}, journal = {1974}, pages = {222--46}, title = {Universal grammar}, year = {1970} } @article{rusu2016progressive, author = {Rusu, A. A. and Rabinowitz, N. C. and Desjardins, G. and Soyer, H. and Kirkpatrick, J. and Kavukcuoglu, K. and Pascanu, R. and Hadsell, R.}, journal = {ArXiv preprint}, title = {Progressive neural networks}, url = {https://arxiv.org/abs/1606.04671}, volume = {abs/1606.04671}, year = {2016} } @article{rasooli-tetrault-2015, author = {Mohammad Sadegh Rasooli and Joel R. Tetreault}, journal = {ArXiv preprint}, title = {Yara Parser: {A} Fast and Accurate Dependency Parser}, url = {https://arxiv.org/abs/1503.06733}, volume = {abs/1503.06733}, year = {2015} } @inproceedings{Bansal2020LearningTF, address = {Barcelona, Spain (Online)}, author = {Bansal, Trapit and Jha, Rishikesh and McCallum, Andrew}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, doi = {10.18653/v1/2020.coling-main.448}, pages = {5108--5123}, publisher = {International Committee on Computational Linguistics}, title = {Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks}, url = {https://aclanthology.org/2020.coling-main.448}, year = {2020} } @inproceedings{lewis-etal-2020-bart, address = {Online}, author = {Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Veselin and Zettlemoyer, Luke}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.703}, pages = {7871--7880}, publisher = {Association for Computational Linguistics}, title = {{BART}: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, url = {https://aclanthology.org/2020.acl-main.703}, year = {2020} } @inproceedings{Finn2017ModelAgnosticMF, author = {Chelsea Finn and Pieter Abbeel and Sergey Levine}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/FinnAL17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {1126--1135}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks}, url = {http://proceedings.mlr.press/v70/finn17a.html}, volume = {70}, year = {2017} } @inproceedings{Houlsby2019ParameterEfficientTL, author = {Neil Houlsby and Andrei Giurgiu and Stanislaw Jastrzebski and Bruna Morrone and Quentin de Laroussilhe and Andrea Gesmundo and Mona Attariyan and Sylvain Gelly}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/HoulsbyGJMLGAG19.bib}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, pages = {2790--2799}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 11 Jun 2019 01:00:00 +0200}, title = {Parameter-Efficient Transfer Learning for {NLP}}, url = {http://proceedings.mlr.press/v97/houlsby19a.html}, volume = {97}, year = {2019} } @article{mccann2018natural, author = {McCann, Bryan and Keskar, Nitish Shirish and Xiong, Caiming and Socher, Richard}, journal = {ArXiv preprint}, title = {The natural language decathlon: Multitask learning as question answering}, url = {https://arxiv.org/abs/1806.08730}, volume = {abs/1806.08730}, year = {2018} } @inproceedings{dAutume2019EpisodicMI, author = {Cyprien de Masson d'Autume and Sebastian Ruder and Lingpeng Kong and Dani Yogatama}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/dAutumeRKY19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {13122--13131}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Episodic Memory in Lifelong Language Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/f8d2e80c1458ea2501f98a2cafadb397-Abstract.html}, year = {2019} } @inproceedings{rusu2018metalearning, author = {Andrei A. Rusu and Dushyant Rao and Jakub Sygnowski and Oriol Vinyals and Razvan Pascanu and Simon Osindero and Raia Hadsell}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/RusuRSVPOH19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Meta-Learning with Latent Embedding Optimization}, url = {https://openreview.net/forum?id=BJgklhAcK7}, year = {2019} } @inproceedings{huang2021continual, address = {Online}, author = {Huang, Yufan and Zhang, Yanzhe and Chen, Jiaao and Wang, Xuezhi and Yang, Diyi}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.218}, pages = {2736--2746}, publisher = {Association for Computational Linguistics}, title = {Continual Learning for Text Classification with Information Disentanglement Based Regularization}, url = {https://aclanthology.org/2021.naacl-main.218}, year = {2021} } @article{Yogatama2019LearningAE, author = {Dani Yogatama and Cyprien de Masson d'Autume and Jerome Connor and Tom{\'a}s Kocisk{\'y} and Mike Chrzanowski and Lingpeng Kong and A. Lazaridou and Wang Ling and L. Yu and Chris Dyer and P. Blunsom}, journal = {ArXiv preprint}, title = {Learning and Evaluating General Linguistic Intelligence}, url = {https://arxiv.org/abs/1901.11373}, volume = {abs/1901.11373}, year = {2019} } @inproceedings{Brown2020LanguageMA, author = {Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert{-}Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Language Models are Few-Shot Learners}, url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html}, year = {2020} } @inproceedings{Gao2020MakingPL, address = {Online}, author = {Gao, Tianyu and Fisch, Adam and Chen, Danqi}, booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, doi = {10.18653/v1/2021.acl-long.295}, pages = {3816--3830}, publisher = {Association for Computational Linguistics}, title = {Making Pre-trained Language Models Better Few-shot Learners}, url = {https://aclanthology.org/2021.acl-long.295}, year = {2021} } @article{Raffel2020ExploringTL, author = {Colin Raffel and Noam M. Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and W. Li and Peter J. Liu}, journal = {ArXiv preprint}, title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer}, url = {https://arxiv.org/abs/1910.10683}, volume = {abs/1910.10683}, year = {2019} } @inproceedings{ha2016hypernetworks, author = {David Ha and Andrew M. Dai and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/HaDL17.bib}, booktitle = {5th International Conference on Learning Representations, {ICLR} 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {HyperNetworks}, url = {https://openreview.net/forum?id=rkpACe1lx}, year = {2017} } @inproceedings{Gidaris2018DynamicFV, author = {Spyros Gidaris and Nikos Komodakis}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/GidarisK18.bib}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, doi = {10.1109/CVPR.2018.00459}, pages = {4367--4375}, publisher = {{IEEE} Computer Society}, timestamp = {Wed, 06 Feb 2019 00:00:00 +0100}, title = {Dynamic Few-Shot Visual Learning Without Forgetting}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Gidaris\_Dynamic\_Few-Shot\_Visual\_CVPR\_2018\_paper.html}, year = {2018} } @inproceedings{Nguyen2018VariationalCL, author = {Cuong V. Nguyen and Yingzhen Li and Thang D. Bui and Richard E. Turner}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/NguyenLBT18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Variational Continual Learning}, url = {https://openreview.net/forum?id=BkQqq0gRb}, year = {2018} } @inproceedings{wang2019sentence, address = {Minneapolis, Minnesota}, author = {Wang, Hong and Xiong, Wenhan and Yu, Mo and Guo, Xiaoxiao and Chang, Shiyu and Wang, William Yang}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1086}, pages = {796--806}, publisher = {Association for Computational Linguistics}, title = {Sentence Embedding Alignment for Lifelong Relation Extraction}, url = {https://aclanthology.org/N19-1086}, year = {2019} } @inproceedings{caccia2020online, author = {Massimo Caccia and Pau Rodr{\'{\i}}guez and Oleksiy Ostapenko and Fabrice Normandin and Min Lin and Lucas Page{-}Caccia and Issam Hadj Laradji and Irina Rish and Alexandre Lacoste and David V{\'{a}}zquez and Laurent Charlin}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/CacciaRONLPLRLV20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Fri, 14 May 2021 01:00:00 +0200}, title = {Online Fast Adaptation and Knowledge Accumulation {(OSAKA):} a New Approach to Continual Learning}, url = {https://proceedings.neurips.cc/paper/2020/hash/c0a271bc0ecb776a094786474322cb82-Abstract.html}, year = {2020} } @article{antoniou2020defining, author = {Antoniou, Antreas and Patacchiola, Massimiliano and Ochal, Mateusz and Storkey, Amos}, journal = {ArXiv preprint}, title = {Defining benchmarks for continual few-shot learning}, url = {https://arxiv.org/abs/2004.11967}, volume = {abs/2004.11967}, year = {2020} } @inproceedings{chatterjee-etal-2019-semeval, address = {Minneapolis, Minnesota, USA}, author = {Chatterjee, Ankush and Narahari, Kedhar Nath and Joshi, Meghana and Agrawal, Puneet}, booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation}, doi = {10.18653/v1/S19-2005}, pages = {39--48}, publisher = {Association for Computational Linguistics}, title = {{S}em{E}val-2019 Task 3: {E}mo{C}ontext Contextual Emotion Detection in Text}, url = {https://aclanthology.org/S19-2005}, year = {2019} } @inproceedings{saravia-etal-2018-carer, address = {Brussels, Belgium}, author = {Saravia, Elvis and Liu, Hsien-Chi Toby and Huang, Yen-Hao and Wu, Junlin and Chen, Yi-Shin}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1404}, pages = {3687--3697}, publisher = {Association for Computational Linguistics}, title = {{CARER}: Contextualized Affect Representations for Emotion Recognition}, url = {https://aclanthology.org/D18-1404}, year = {2018} } @inproceedings{williams-etal-2018-broad, address = {New Orleans, Louisiana}, author = {Williams, Adina and Nangia, Nikita and Bowman, Samuel}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1101}, pages = {1112--1122}, publisher = {Association for Computational Linguistics}, title = {A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference}, url = {https://aclanthology.org/N18-1101}, year = {2018} } @inproceedings{dolan-brockett-2005-automatically, author = {Dolan, William B. and Brockett, Chris}, booktitle = {Proceedings of the Third International Workshop on Paraphrasing ({IWP}2005)}, title = {Automatically Constructing a Corpus of Sentential Paraphrases}, url = {https://aclanthology.org/I05-5002}, year = {2005} } @inproceedings{socher-etal-2013-recursive, address = {Seattle, Washington, USA}, author = {Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher}, booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing}, pages = {1631--1642}, publisher = {Association for Computational Linguistics}, title = {Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank}, url = {https://aclanthology.org/D13-1170}, year = {2013} } @inproceedings{rajpurkar-etal-2016-squad, address = {Austin, Texas}, author = {Rajpurkar, Pranav and Zhang, Jian and Lopyrev, Konstantin and Liang, Percy}, booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D16-1264}, pages = {2383--2392}, publisher = {Association for Computational Linguistics}, title = {{SQ}u{AD}: 100,000+ Questions for Machine Comprehension of Text}, url = {https://aclanthology.org/D16-1264}, year = {2016} } @inproceedings{maas-etal-2011-learning, address = {Portland, Oregon, USA}, author = {Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher}, booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies}, pages = {142--150}, publisher = {Association for Computational Linguistics}, title = {Learning Word Vectors for Sentiment Analysis}, url = {https://aclanthology.org/P11-1015}, year = {2011} } @inproceedings{faruqui-pado-2011-thou, address = {Portland, Oregon, USA}, author = {Faruqui, Manaal and Pad{\'o}, Sebastian}, booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies}, pages = {467--472}, publisher = {Association for Computational Linguistics}, title = {{``}{I} Thou Thee, Thou Traitor{''}: Predicting Formal vs. Informal Address in {E}nglish Literature}, url = {https://aclanthology.org/P11-2082}, year = {2011} } @inproceedings{thorne-etal-2017-fake, address = {Copenhagen, Denmark}, author = {Thorne, James and Chen, Mingjie and Myrianthous, Giorgos and Pu, Jiashu and Wang, Xiaoxuan and Vlachos, Andreas}, booktitle = {Proceedings of the 2017 {EMNLP} Workshop: Natural Language Processing meets Journalism}, doi = {10.18653/v1/W17-4214}, pages = {80--83}, publisher = {Association for Computational Linguistics}, title = {Fake news stance detection using stacked ensemble of classifiers}, url = {https://aclanthology.org/W17-4214}, year = {2017} } @inproceedings{vajjala-banerjee-2017-study, address = {Copenhagen, Denmark}, author = {Vajjala, Sowmya and Banerjee, Sagnik}, booktitle = {Proceedings of the 12th Workshop on Innovative Use of {NLP} for Building Educational Applications}, doi = {10.18653/v1/W17-5026}, pages = {240--248}, publisher = {Association for Computational Linguistics}, title = {A study of N-gram and Embedding Representations for Native Language Identification}, url = {https://aclanthology.org/W17-5026}, year = {2017} } @inproceedings{zhang-etal-2019-paws, address = {Minneapolis, Minnesota}, author = {Zhang, Yuan and Baldridge, Jason and He, Luheng}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1131}, pages = {1298--1308}, publisher = {Association for Computational Linguistics}, title = {{PAWS}: Paraphrase Adversaries from Word Scrambling}, url = {https://aclanthology.org/N19-1131}, year = {2019} } @inproceedings{pilehvar-camacho-collados-2019-wic, address = {Minneapolis, Minnesota}, author = {Pilehvar, Mohammad Taher and Camacho-Collados, Jose}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1128}, pages = {1267--1273}, publisher = {Association for Computational Linguistics}, title = {{W}i{C}: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations}, url = {https://aclanthology.org/N19-1128}, year = {2019} } @inproceedings{li-roth-2002-learning, author = {Li, Xin and Roth, Dan}, booktitle = {{COLING} 2002: The 19th International Conference on Computational Linguistics}, title = {Learning Question Classifiers}, url = {https://aclanthology.org/C02-1150}, year = {2002} } @inproceedings{hovy-etal-2001-toward, author = {Hovy, Eduard and Gerber, Laurie and Hermjakob, Ulf and Lin, Chin-Yew and Ravichandran, Deepak}, booktitle = {Proceedings of the First International Conference on Human Language Technology Research}, title = {Toward Semantics-Based Answer Pinpointing}, url = {https://aclanthology.org/H01-1069}, year = {2001} } @inproceedings{yang-etal-2015-wikiqa, address = {Lisbon, Portugal}, author = {Yang, Yi and Yih, Wen-tau and Meek, Christopher}, booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D15-1237}, pages = {2013--2018}, publisher = {Association for Computational Linguistics}, title = {{W}iki{QA}: A Challenge Dataset for Open-Domain Question Answering}, url = {https://aclanthology.org/D15-1237}, year = {2015} } @inproceedings{faruqui-das-2018-identifying, address = {Brussels, Belgium}, author = {Faruqui, Manaal and Das, Dipanjan}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1091}, pages = {798--803}, publisher = {Association for Computational Linguistics}, title = {Identifying Well-formed Natural Language Questions}, url = {https://aclanthology.org/D18-1091}, year = {2018} } @inproceedings{thorne-etal-2018-fever, address = {New Orleans, Louisiana}, author = {Thorne, James and Vlachos, Andreas and Christodoulopoulos, Christos and Mittal, Arpit}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1074}, pages = {809--819}, publisher = {Association for Computational Linguistics}, title = {{FEVER}: a Large-scale Dataset for Fact Extraction and {VER}ification}, url = {https://aclanthology.org/N18-1074}, year = {2018} } @inproceedings{wang-2017-liar, address = {Vancouver, Canada}, author = {Wang, William Yang}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, doi = {10.18653/v1/P17-2067}, pages = {422--426}, publisher = {Association for Computational Linguistics}, title = {{``}Liar, Liar Pants on Fire{''}: A New Benchmark Dataset for Fake News Detection}, url = {https://aclanthology.org/P17-2067}, year = {2017} } @article{GURULINGAPPA2012885, abstract = {A significant amount of information about drug-related safety issues such as adverse effects are published in medical case reports that can only be explored by human readers due to their unstructured nature. The work presented here aims at generating a systematically annotated corpus that can support the development and validation of methods for the automatic extraction of drug-related adverse effects from medical case reports. The documents are systematically double annotated in various rounds to ensure consistent annotations. The annotated documents are finally harmonized to generate representative consensus annotations. In order to demonstrate an example use case scenario, the corpus was employed to train and validate models for the classification of informative against the non-informative sentences. A Maximum Entropy classifier trained with simple features and evaluated by 10-fold cross-validation resulted in the F1 score of 0.70 indicating a potential useful application of the corpus.}, author = {Harsha Gurulingappa and Abdul Mateen Rajput and Angus Roberts and Juliane Fluck and Martin Hofmann-Apitius and Luca Toldo}, doi = {https://doi.org/10.1016/j.jbi.2012.04.008}, issn = {1532-0464}, journal = {Journal of Biomedical Informatics}, keywords = {Adverse drug effect, Benchmark corpus, Annotation, Harmonization, Sentence classification}, note = {Text Mining and Natural Language Processing in Pharmacogenomics}, number = {5}, pages = {885-892}, title = {Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports}, url = {https://www.sciencedirect.com/science/article/pii/S1532046412000615}, volume = {45}, year = {2012} } @article{bartolo-etal-2020-beat, address = {Cambridge, MA}, author = {Bartolo, Max and Roberts, Alastair and Welbl, Johannes and Riedel, Sebastian and Stenetorp, Pontus}, doi = {10.1162/tacl_a_00338}, journal = {Transactions of the Association for Computational Linguistics}, pages = {662--678}, publisher = {MIT Press}, title = {Beat the {AI}: Investigating Adversarial Human Annotation for Reading Comprehension}, url = {https://aclanthology.org/2020.tacl-1.43}, volume = {8}, year = {2020} } @article{Clark2018ThinkYH, author = {Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord}, journal = {ArXiv preprint}, title = {Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge}, url = {https://arxiv.org/abs/1803.05457}, volume = {abs/1803.05457}, year = {2018} } @inproceedings{McAuley2013HiddenFA, author = {Julian J. McAuley and Jure Leskovec}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/recsys/McAuleyL13.bib}, booktitle = {Seventh {ACM} Conference on Recommender Systems, RecSys '13, Hong Kong, China, October 12-16, 2013}, doi = {10.1145/2507157.2507163}, editor = {Qiang Yang and Irwin King and Qing Li and Pearl Pu and George Karypis}, pages = {165--172}, publisher = {{ACM}}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, title = {Hidden factors and hidden topics: understanding rating dimensions with review text}, url = {https://doi.org/10.1145/2507157.2507163}, year = {2013} } @inproceedings{nie-etal-2020-adversarial, address = {Online}, author = {Nie, Yixin and Williams, Adina and Dinan, Emily and Bansal, Mohit and Weston, Jason and Kiela, Douwe}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.441}, pages = {4885--4901}, publisher = {Association for Computational Linguistics}, title = {Adversarial {NLI}: A New Benchmark for Natural Language Understanding}, url = {https://aclanthology.org/2020.acl-main.441}, year = {2020} } @inproceedings{app-review, authors = {Grano, Giovanni ahd Di Sorbo, Andrea and Mercaldo, Francesco and Visaggio, Corrado A and Canfora, Gerardo and Panichella, Sebastiano}, title = {Software Applications User Reviews}, year = {2017} } @inproceedings{bhagavatula2020abductive, author = {Chandra Bhagavatula and Ronan Le Bras and Chaitanya Malaviya and Keisuke Sakaguchi and Ari Holtzman and Hannah Rashkin and Doug Downey and Wen{-}tau Yih and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/BhagavatulaBMSH20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Abductive Commonsense Reasoning}, url = {https://openreview.net/forum?id=Byg1v1HKDB}, year = {2020} } @inproceedings{Othman2012EnglishASLGP, author = {A. Othman and M. Jemni}, title = {English-ASL Gloss Parallel Corpus 2012: ASLG-PC12}, year = {2012} } @inproceedings{pappas-etal-2020-biomrc, address = {Online}, author = {Pappas, Dimitris and Stavropoulos, Petros and Androutsopoulos, Ion and McDonald, Ryan}, booktitle = {Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing}, doi = {10.18653/v1/2020.bionlp-1.15}, pages = {140--149}, publisher = {Association for Computational Linguistics}, title = {{B}io{MRC}: A Dataset for Biomedical Machine Reading Comprehension}, url = {https://aclanthology.org/2020.bionlp-1.15}, year = {2020} } @article{warstadt2019blimp, address = {Cambridge, MA}, author = {Warstadt, Alex and Parrish, Alicia and Liu, Haokun and Mohananey, Anhad and Peng, Wei and Wang, Sheng-Fu and Bowman, Samuel R.}, doi = {10.1162/tacl_a_00321}, journal = {Transactions of the Association for Computational Linguistics}, pages = {377--392}, publisher = {MIT Press}, title = {{BL}i{MP}: The Benchmark of Linguistic Minimal Pairs for {E}nglish}, url = {https://aclanthology.org/2020.tacl-1.25}, volume = {8}, year = {2020} } @article{wolfson-etal-2020-break, address = {Cambridge, MA}, author = {Wolfson, Tomer and Geva, Mor and Gupta, Ankit and Gardner, Matt and Goldberg, Yoav and Deutch, Daniel and Berant, Jonathan}, doi = {10.1162/tacl_a_00309}, journal = {Transactions of the Association for Computational Linguistics}, pages = {183--198}, publisher = {MIT Press}, title = {Break It Down: A Question Understanding Benchmark}, url = {https://aclanthology.org/2020.tacl-1.13}, volume = {8}, year = {2020} } @inproceedings{louis-etal-2020-id, address = {Online}, author = {Louis, Annie and Roth, Dan and Radlinski, Filip}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.601}, pages = {7411--7425}, publisher = {Association for Computational Linguistics}, title = {{``}{I}{'}d rather just go to bed{''}: Understanding Indirect Answers}, url = {https://aclanthology.org/2020.emnlp-main.601}, year = {2020} } @article{Diggelmann2020CLIMATEFEVERAD, author = {T. Diggelmann and Jordan L. Boyd-Graber and Jannis Bulian and Massimiliano Ciaramita and Markus Leippold}, journal = {ArXiv preprint}, title = {CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims}, url = {https://arxiv.org/abs/2012.00614}, volume = {abs/2012.00614}, year = {2020} } @inproceedings{lin-etal-2020-commongen, address = {Online}, author = {Lin, Bill Yuchen and Zhou, Wangchunshu and Shen, Ming and Zhou, Pei and Bhagavatula, Chandra and Choi, Yejin and Ren, Xiang}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.165}, pages = {1823--1840}, publisher = {Association for Computational Linguistics}, title = {{C}ommon{G}en: A Constrained Text Generation Challenge for Generative Commonsense Reasoning}, url = {https://aclanthology.org/2020.findings-emnlp.165}, year = {2020} } @inproceedings{zhang-etal-2020-semi, address = {Barcelona, Spain (Online)}, author = {Zhang, Hao and Ro, Jae and Sproat, Richard}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, doi = {10.18653/v1/2020.coling-main.411}, pages = {4667--4675}, publisher = {International Committee on Computational Linguistics}, title = {Semi-supervised {URL} Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities}, url = {https://aclanthology.org/2020.coling-main.411}, year = {2020} } @inproceedings{nangia-etal-2020-crows, address = {Online}, author = {Nangia, Nikita and Vania, Clara and Bhalerao, Rasika and Bowman, Samuel R.}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.154}, pages = {1953--1967}, publisher = {Association for Computational Linguistics}, title = {{C}row{S}-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models}, url = {https://aclanthology.org/2020.emnlp-main.154}, year = {2020} } @article{Lehmann2015DBpediaA, author = {Jens Lehmann and Robert Isele and Max Jakob and Anja Jentzsch and D. Kontokostas and Pablo N. Mendes and Sebastian Hellmann and M. Morsey and Patrick van Kleef and S. Auer and C. Bizer}, journal = {Semantic Web}, pages = {167-195}, title = {DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia}, volume = {6}, year = {2015} } @article{dusek.etal2020:csl, archiveprefix = {arXiv}, author = {Du{\v{s}}ek, Ond\v{r}ej and Novikova, Jekaterina and Rieser, Verena}, doi = {10.1016/j.csl.2019.06.009}, eprint = {1901.11528}, eprinttype = {arxiv}, journal = {Computer Speech \& Language}, pages = {123--156}, title = {Evaluating the {{State}}-of-the-{{Art}} of {{End}}-to-{{End Natural Language Generation}}: {{The E2E NLG Challenge}}}, volume = {59}, year = {2020} } @inproceedings{dusek-etal-2019-semantic, address = {Tokyo, Japan}, author = {Du{\v{s}}ek, Ond{\v{r}}ej and Howcroft, David M. and Rieser, Verena}, booktitle = {Proceedings of the 12th International Conference on Natural Language Generation}, doi = {10.18653/v1/W19-8652}, pages = {421--426}, publisher = {Association for Computational Linguistics}, title = {Semantic Noise Matters for Neural Natural Language Generation}, url = {https://aclanthology.org/W19-8652}, year = {2019} } @article{Mollas2020ETHOSAO, author = {Ioannis Mollas and Zoe Chrysopoulou and Stamatis Karlos and Grigorios Tsoumakas}, journal = {ArXiv preprint}, title = {ETHOS: an Online Hate Speech Detection Dataset}, url = {https://arxiv.org/abs/2006.08328}, volume = {abs/2006.08328}, year = {2020} } @article{financial-phrasebank, abstract = {The use of robo-readers to analyze news texts is an emerging technology trend in computational finance. Recent research has developed sophisticated financial polarity lexicons for investigating how financial sentiments relate to future company performance. However, based on experience from fields that commonly analyze sentiment, it is well known that the overall semantic orientation of a sentence may differ from that of individual words. This article investigates how semantic orientations can be better detected in financial and economic news by accommodating the overall phrase-structure information and domain-specific use of language. Our three main contributions are the following: a a human-annotated finance phrase bank that can be used for training and evaluating alternative models; b a technique to enhance financial lexicons with attributes that help to identify expected direction of events that affect sentiment; and c a linearized phrase-structure model for detecting contextual semantic orientations in economic texts. The relevance of the newly added lexicon features and the benefit of using the proposed learning algorithm are demonstrated in a comparative study against general sentiment models as well as the popular word frequency models used in recent financial studies. The proposed framework is parsimonious and avoids the explosion in feature space caused by the use of conventional n-gram features.}, address = {USA}, author = {Malo, Pekka and Sinha, Ankur and Korhonen, Pekka and Wallenius, Jyrki and Takala, Pyry}, doi = {10.1002/asi.23062}, issn = {2330-1635}, issue_date = {April 2014}, journal = {J. Assoc. Inf. Sci. Technol.}, keywords = {automatic classification, linguistic analysis, economics}, number = {4}, numpages = {15}, pages = {782–796}, publisher = {John Wiley & Sons, Inc.}, title = {Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts}, url = {https://doi.org/10.1002/asi.23062}, volume = {65}, year = {2014} } @article{warstadt-etal-2019-neural, address = {Cambridge, MA}, author = {Warstadt, Alex and Singh, Amanpreet and Bowman, Samuel R.}, doi = {10.1162/tacl_a_00290}, journal = {Transactions of the Association for Computational Linguistics}, pages = {625--641}, publisher = {MIT Press}, title = {Neural Network Acceptability Judgments}, url = {https://aclanthology.org/Q19-1040}, volume = {7}, year = {2019} } @inproceedings{dagan2005pascal, author = {Dagan, Ido and Glickman, Oren and Magnini, Bernardo}, booktitle = {Machine Learning Challenges Workshop}, organization = {Springer}, pages = {177--190}, title = {The PASCAL recognising textual entailment challenge}, year = {2005} } @inproceedings{bar2006second, author = {Bar-Haim, Roy and Dagan, Ido and Dolan, Bill and Ferro, Lisa and Giampiccolo, Danilo and Magnini, Bernardo and Szpektor, Idan}, booktitle = {Proceedings of the second PASCAL challenges workshop on recognising textual entailment}, number = {1}, organization = {Venice}, pages = {6--4}, title = {The second pascal recognising textual entailment challenge}, volume = {6}, year = {2006} } @inproceedings{giampiccolo2007third, address = {Prague}, author = {Giampiccolo, Danilo and Magnini, Bernardo and Dagan, Ido and Dolan, Bill}, booktitle = {Proceedings of the {ACL}-{PASCAL} Workshop on Textual Entailment and Paraphrasing}, pages = {1--9}, publisher = {Association for Computational Linguistics}, title = {The Third {PASCAL} Recognizing Textual Entailment Challenge}, url = {https://aclanthology.org/W07-1401}, year = {2007} } @inproceedings{bentivogli2009fifth, author = {Bentivogli, Luisa and Clark, Peter and Dagan, Ido and Giampiccolo, Danilo}, booktitle = {TAC}, title = {The Fifth PASCAL Recognizing Textual Entailment Challenge.}, year = {2009} } @inproceedings{levesque2012winograd, abstract = {In this paper, we present an alternative to the Turing Test that has some conceptual and practical advantages. A Wino-grad schema is a pair of sentences that differ only in one or two words and that contain a referential ambiguity that is resolved in opposite directions in the two sentences. We have compiled a collection of Winograd schemas, designed so that the correct answer is obvious to the human reader, but cannot easily be found using selectional restrictions or statistical techniques over text corpora. A contestant in the Winograd Schema Challenge is presented with a collection of one sentence from each pair, and required to achieve human-level accuracy in choosing the correct disambiguation.}, author = {Levesque, Hector J. and Davis, Ernest and Morgenstern, Leora}, booktitle = {Proceedings of the Thirteenth International Conference on Principles of Knowledge Representation and Reasoning}, isbn = {9781577355601}, location = {Rome, Italy}, numpages = {10}, pages = {552–561}, publisher = {AAAI Press}, series = {KR'12}, title = {The Winograd Schema Challenge}, year = {2012} } @inproceedings{gibert2018hate, address = {Brussels, Belgium}, author = {de Gibert, Ona and Perez, Naiara and Garc{\'\i}a-Pablos, Aitor and Cuadros, Montse}, booktitle = {Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)}, doi = {10.18653/v1/W18-5102}, pages = {11--20}, publisher = {Association for Computational Linguistics}, title = {Hate Speech Dataset from a White Supremacy Forum}, url = {https://aclanthology.org/W18-5102}, year = {2018} } @inproceedings{hateoffensive, author = {Davidson, Thomas and Warmsley, Dana and Macy, Michael and Weber, Ingmar}, booktitle = {Proceedings of the 11th International AAAI Conference on Web and Social Media}, location = {Montreal, Canada}, pages = {512-515}, series = {ICWSM '17}, title = {Automated Hate Speech Detection and the Problem of Offensive Language}, year = {2017} } @article{mathew2020hatexplain, author = {Mathew, Binny and Saha, Punyajoy and Yimam, Seid Muhie and Biemann, Chris and Goyal, Pawan and Mukherjee, Animesh}, journal = {ArXiv preprint}, title = {HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection}, url = {https://arxiv.org/abs/2012.10289}, volume = {abs/2012.10289}, year = {2020} } @inproceedings{kotonya-toni-2020-explainable-automated, address = {Online}, author = {Kotonya, Neema and Toni, Francesca}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.623}, pages = {7740--7754}, publisher = {Association for Computational Linguistics}, title = {Explainable Automated Fact-Checking for Public Health Claims}, url = {https://aclanthology.org/2020.emnlp-main.623}, year = {2020} } @inproceedings{dinan2018wizard, author = {Emily Dinan and Stephen Roller and Kurt Shuster and Angela Fan and Michael Auli and Jason Weston}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/DinanRSFAW19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 30 Jul 2020 01:00:00 +0200}, title = {Wizard of Wikipedia: Knowledge-Powered Conversational Agents}, url = {https://openreview.net/forum?id=r1l73iRqKm}, year = {2019} } @inproceedings{petroni2020how, author = {Fabio Petroni and Patrick Lewis and Aleksandra Piktus and Tim Rockt{\""a}schel and Yuxiang Wu and Alexander H. Miller and Sebastian Riedel}, booktitle = {Automated Knowledge Base Construction}, title = {How Context Affects Language Models' Factual Predictions}, url = {https://openreview.net/forum?id=025X0zPfn}, year = {2020} } @inproceedings{petroni-etal-2019-language, address = {Hong Kong, China}, author = {Petroni, Fabio and Rockt{\""a}schel, Tim and Riedel, Sebastian and Lewis, Patrick and Bakhtin, Anton and Wu, Yuxiang and Miller, Alexander}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1250}, pages = {2463--2473}, publisher = {Association for Computational Linguistics}, title = {Language Models as Knowledge Bases?}, url = {https://aclanthology.org/D19-1250}, year = {2019} } @inproceedings{manotas-etal-2020-limit, address = {Online}, author = {Manotas, Irene and Vo, Ngoc Phuoc An and Sheinin, Vadim}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.88}, pages = {991--1000}, publisher = {Association for Computational Linguistics}, title = {{L}i{M}i{T}: The Literal Motion in Text Dataset}, url = {https://aclanthology.org/2020.findings-emnlp.88}, year = {2020} } @inproceedings{zhou-etal-2019-going, address = {Hong Kong, China}, author = {Zhou, Ben and Khashabi, Daniel and Ning, Qiang and Roth, Dan}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1332}, pages = {3363--3369}, publisher = {Association for Computational Linguistics}, title = {{``}Going on a vacation{''} takes longer than {``}Going for a walk{''}: A Study of Temporal Commonsense Understanding}, url = {https://aclanthology.org/D19-1332}, year = {2019} } @inproceedings{medical-qqp, author = {Clara H. McCreery and Namit Katariya and Anitha Kannan and Manish Chablani and Xavier Amatriain}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/kdd/McCreeryKKCA20.bib}, booktitle = {{KDD} '20: The 26th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020}, editor = {Rajesh Gupta and Yan Liu and Jiliang Tang and B. Aditya Prakash}, pages = {3458--3465}, publisher = {{ACM}}, timestamp = {Mon, 24 Aug 2020 01:00:00 +0200}, title = {Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to {COVID-19} FAQs}, url = {https://dl.acm.org/doi/10.1145/3394486.3412861}, year = {2020} } @inproceedings{chen-etal-2020-mocha, address = {Online}, author = {Chen, Anthony and Stanovsky, Gabriel and Singh, Sameer and Gardner, Matt}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.528}, pages = {6521--6532}, publisher = {Association for Computational Linguistics}, title = {{MOCHA}: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics}, url = {https://aclanthology.org/2020.emnlp-main.528}, year = {2020} } @inproceedings{lin-etal-2020-birds, address = {Online}, author = {Lin, Bill Yuchen and Lee, Seyeon and Khanna, Rahul and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.557}, pages = {6862--6868}, publisher = {Association for Computational Linguistics}, title = {{B}irds have four legs?! {N}umer{S}ense: {P}robing {N}umerical {C}ommonsense {K}nowledge of {P}re-{T}rained {L}anguage {M}odels}, url = {https://aclanthology.org/2020.emnlp-main.557}, year = {2020} } @inproceedings{Bisk2020, author = {Yonatan Bisk and Rowan Zellers and Ronan LeBras and Jianfeng Gao and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/BiskZLGC20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {7432--7439}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {{PIQA:} Reasoning about Physical Commonsense in Natural Language}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6239}, year = {2020} } @inproceedings{sheng-uthus-2020-investigating, address = {Barcelona, Spain (Online)}, author = {Sheng, Emily and Uthus, David}, booktitle = {Proceedings of the Second Workshop on Gender Bias in Natural Language Processing}, pages = {93--106}, publisher = {Association for Computational Linguistics}, title = {Investigating Societal Biases in a Poetry Composition System}, url = {https://aclanthology.org/2020.gebnlp-1.9}, year = {2020} } @inproceedings{boratko-etal-2020-protoqa, address = {Online}, author = {Boratko, Michael and Li, Xiang and O{'}Gorman, Tim and Das, Rajarshi and Le, Dan and McCallum, Andrew}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.85}, pages = {1122--1136}, publisher = {Association for Computational Linguistics}, title = {{P}roto{QA}: A Question Answering Dataset for Prototypical Common-Sense Reasoning}, url = {https://aclanthology.org/2020.emnlp-main.85}, year = {2020} } @inproceedings{tafjord-etal-2019-quartz, address = {Hong Kong, China}, author = {Tafjord, Oyvind and Gardner, Matt and Lin, Kevin and Clark, Peter}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1608}, pages = {5941--5946}, publisher = {Association for Computational Linguistics}, title = {{Q}ua{RT}z: An Open-Domain Dataset of Qualitative Relationship Questions}, url = {https://aclanthology.org/D19-1608}, year = {2019} } @inproceedings{dasigi-etal-2019-quoref, address = {Hong Kong, China}, author = {Dasigi, Pradeep and Liu, Nelson F. and Marasovi{\'c}, Ana and Smith, Noah A. and Gardner, Matt}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1606}, pages = {5925--5932}, publisher = {Association for Computational Linguistics}, title = {{Q}uoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning}, url = {https://aclanthology.org/D19-1606}, year = {2019} } @inproceedings{lin-etal-2019-reasoning, address = {Hong Kong, China}, author = {Lin, Kevin and Tafjord, Oyvind and Clark, Peter and Gardner, Matt}, booktitle = {Proceedings of the 2nd Workshop on Machine Reading for Question Answering}, doi = {10.18653/v1/D19-5808}, pages = {58--62}, publisher = {Association for Computational Linguistics}, title = {Reasoning Over Paragraph Effects in Situations}, url = {https://aclanthology.org/D19-5808}, year = {2019} } @inproceedings{gliwa-etal-2019-samsum, address = {Hong Kong, China}, author = {Gliwa, Bogdan and Mochol, Iwona and Biesek, Maciej and Wawer, Aleksander}, booktitle = {Proceedings of the 2nd Workshop on New Frontiers in Summarization}, doi = {10.18653/v1/D19-5409}, pages = {70--79}, publisher = {Association for Computational Linguistics}, title = {{SAMS}um Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization}, url = {https://aclanthology.org/D19-5409}, year = {2019} } @inproceedings{scitail, author = {Tushar Khot and Ashish Sabharwal and Peter Clark}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/KhotSC18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {5189--5197}, publisher = {{AAAI} Press}, timestamp = {Mon, 22 Oct 2018 01:00:00 +0200}, title = {SciTaiL: {A} Textual Entailment Dataset from Science Question Answering}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17368}, year = {2018} } @inproceedings{sms_spam, abstract = {The growth of mobile phone users has lead to a dramatic increasing of SMS spam messages. In practice, fighting mobile phone spam is difficult by several factors, including the lower rate of SMS that has allowed many users and service providers to ignore the issue, and the limited availability of mobile phone spam-filtering software. On the other hand, in academic settings, a major handicap is the scarcity of public SMS spam datasets, that are sorely needed for validation and comparison of different classifiers. Moreover, as SMS messages are fairly short, content-based spam filters may have their performance degraded. In this paper, we offer a new real, public and non-encoded SMS spam collection that is the largest one as far as we know. Moreover, we compare the performance achieved by several established machine learning methods. The results indicate that Support Vector Machine outperforms other evaluated classifiers and, hence, it can be used as a good baseline for further comparison.}, address = {New York, NY, USA}, author = {Almeida, Tiago A. and Hidalgo, Jos\'{e} Mar\'{\i}a G. and Yamakami, Akebo}, booktitle = {Proceedings of the 11th ACM Symposium on Document Engineering}, doi = {10.1145/2034691.2034742}, isbn = {9781450308632}, keywords = {mobile spam, spam filtering, classification}, location = {Mountain View, California, USA}, numpages = {4}, pages = {259–262}, publisher = {Association for Computing Machinery}, series = {DocEng '11}, title = {Contributions to the Study of SMS Spam Filtering: New Collection and Results}, url = {https://doi.org/10.1145/2034691.2034742}, year = {2011} } @article{Zhang2018ReCoRDBT, author = {Sheng Zhang and X. Liu and J. Liu and Jianfeng Gao and Kevin Duh and Benjamin Van Durme}, journal = {ArXiv preprint}, title = {ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension}, url = {https://arxiv.org/abs/1810.12885}, volume = {abs/1810.12885}, year = {2018} } @inproceedings{Chen2020TabFact, author = {Wenhu Chen and Hongmin Wang and Jianshu Chen and Yunkai Zhang and Hong Wang and Shiyang Li and Xiyou Zhou and William Yang Wang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ChenWCZWLZW20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {TabFact: {A} Large-scale Dataset for Table-based Fact Verification}, url = {https://openreview.net/forum?id=rkeJRhNYDH}, year = {2020} } @inproceedings{barbieri-etal-2020-tweeteval, address = {Online}, author = {Barbieri, Francesco and Camacho-Collados, Jose and Espinosa Anke, Luis and Neves, Leonardo}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.148}, pages = {1644--1650}, publisher = {Association for Computational Linguistics}, title = {{T}weet{E}val: Unified Benchmark and Comparative Evaluation for Tweet Classification}, url = {https://aclanthology.org/2020.findings-emnlp.148}, year = {2020} } @inproceedings{jiang-etal-2020-neural, address = {Online}, author = {Jiang, Chao and Maddela, Mounica and Lan, Wuwei and Zhong, Yang and Xu, Wei}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.709}, pages = {7943--7960}, publisher = {Association for Computational Linguistics}, title = {Neural {CRF} Model for Sentence Alignment in Text Simplification}, url = {https://aclanthology.org/2020.acl-main.709}, year = {2020} } @article{zhongSeq2SQL2017, author = {Victor Zhong an}, journal = {ArXiv preprint}, title = {Seq2SQL: Generating Structured Queries from Natural Language usin}, url = {https://arxiv.org/abs/1709.00103}, volume = {abs/1709.00103}, year = {2017} } @inproceedings{tandon-etal-2019-wiqa, address = {Hong Kong, China}, author = {Tandon, Niket and Dalvi, Bhavana and Sakaguchi, Keisuke and Clark, Peter and Bosselut, Antoine}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1629}, pages = {6076--6085}, publisher = {Association for Computational Linguistics}, title = {{WIQA}: A dataset for {``}What if...{''} reasoning over procedural text}, url = {https://aclanthology.org/D19-1629}, year = {2019} } @inproceedings{zhang2015character, author = {Xiang Zhang and Junbo Jake Zhao and Yann LeCun}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ZhangZL15.bib}, booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada}, editor = {Corinna Cortes and Neil D. Lawrence and Daniel D. Lee and Masashi Sugiyama and Roman Garnett}, pages = {649--657}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Character-level Convolutional Networks for Text Classification}, url = {https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html}, year = {2015} } @inproceedings{sileo-etal-2019-mining, address = {Minneapolis, Minnesota}, author = {Sileo, Damien and Van De Cruys, Tim and Pradel, Camille and Muller, Philippe}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1351}, pages = {3477--3486}, publisher = {Association for Computational Linguistics}, title = {Mining Discourse Markers for Unsupervised Sentence Representation Learning}, url = {https://aclanthology.org/N19-1351}, year = {2019} } @inproceedings{schwarz2018progress, author = {Jonathan Schwarz and Wojciech Czarnecki and Jelena Luketina and Agnieszka Grabska{-}Barwinska and Yee Whye Teh and Razvan Pascanu and Raia Hadsell}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/Schwarz0LGTPH18.bib}, booktitle = {Proceedings of the 35th International Conference on Machine Learning, {ICML} 2018, Stockholmsm{\""{a}}ssan, Stockholm, Sweden, July 10-15, 2018}, editor = {Jennifer G. Dy and Andreas Krause}, pages = {4535--4544}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Progress {\&} Compress: {A} scalable framework for continual learning}, url = {http://proceedings.mlr.press/v80/schwarz18a.html}, volume = {80}, year = {2018} } @inproceedings{brown2020language, author = {Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert{-}Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Language Models are Few-Shot Learners}, url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html}, year = {2020} } @inproceedings{verga2020facts, author = {Verga, Pat and Sun, Haitian and Soares, Livio Baldini and Cohen, William W}, booktitle = {NAACL}, title = {Facts as experts: Adaptable and interpretable neural memory over symbolic knowledge}, year = {2021} } @inproceedings{fevry2020entities, address = {Online}, author = {F{\'e}vry, Thibault and Baldini Soares, Livio and FitzGerald, Nicholas and Choi, Eunsol and Kwiatkowski, Tom}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.400}, pages = {4937--4951}, publisher = {Association for Computational Linguistics}, title = {Entities as Experts: Sparse Memory Access with Entity Supervision}, url = {https://aclanthology.org/2020.emnlp-main.400}, year = {2020} } @inproceedings{tenney2019bert, address = {Florence, Italy}, author = {Tenney, Ian and Das, Dipanjan and Pavlick, Ellie}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1452}, pages = {4593--4601}, publisher = {Association for Computational Linguistics}, title = {{BERT} Rediscovers the Classical {NLP} Pipeline}, url = {https://aclanthology.org/P19-1452}, year = {2019} } @article{zhu2020modifying, author = {Zhu, Chen and Rawat, Ankit Singh and Zaheer, Manzil and Bhojanapalli, Srinadh and Li, Daliang and Yu, Felix and Kumar, Sanjiv}, journal = {ArXiv preprint}, title = {Modifying Memories in Transformer Models}, url = {https://arxiv.org/abs/2012.00363}, volume = {abs/2012.00363}, year = {2020} } @inproceedings{joshi2017triviaqa, address = {Vancouver, Canada}, author = {Joshi, Mandar and Choi, Eunsol and Weld, Daniel and Zettlemoyer, Luke}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1147}, pages = {1601--1611}, publisher = {Association for Computational Linguistics}, title = {{T}rivia{QA}: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension}, url = {https://aclanthology.org/P17-1147}, year = {2017} } @inproceedings{chen2020recall, address = {Online}, author = {Chen, Sanyuan and Hou, Yutai and Cui, Yiming and Che, Wanxiang and Liu, Ting and Yu, Xiangzhan}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.634}, pages = {7870--7881}, publisher = {Association for Computational Linguistics}, title = {Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting}, url = {https://aclanthology.org/2020.emnlp-main.634}, year = {2020} } @inproceedings{wang2020k, address = {Online}, author = {Wang, Ruize and Tang, Duyu and Duan, Nan and Wei, Zhongyu and Huang, Xuanjing and Ji, Jianshu and Cao, Guihong and Jiang, Daxin and Zhou, Ming}, booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021}, doi = {10.18653/v1/2021.findings-acl.121}, pages = {1405--1418}, publisher = {Association for Computational Linguistics}, title = {{K-Adapter}: {I}nfusing {K}nowledge into {P}re-{T}rained {M}odels with {A}dapters}, url = {https://aclanthology.org/2021.findings-acl.121}, year = {2021} } @article{patterson2021carbon, author = {Patterson, David and Gonzalez, Joseph and Le, Quoc and Liang, Chen and Munguia, Lluis-Miquel and Rothchild, Daniel and So, David and Texier, Maud and Dean, Jeff}, journal = {ArXiv preprint}, title = {Carbon emissions and large neural network training}, url = {https://arxiv.org/abs/2104.10350}, volume = {abs/2104.10350}, year = {2021} } @inproceedings{hamborg2017news, author = {Hamborg, Felix and Meuschke, Norman and Breitinger, Corinna and Gipp, Bela}, booktitle = {15th International Symposium of Information Science (ISI 2017)}, pages = {218--223}, title = {news-please: A generic news crawler and extractor}, year = {2017} } @inproceedings{zellers2019defending, author = {Rowan Zellers and Ari Holtzman and Hannah Rashkin and Yonatan Bisk and Ali Farhadi and Franziska Roesner and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ZellersHRBFRC19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {9051--9062}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Defending Against Neural Fake News}, url = {https://proceedings.neurips.cc/paper/2019/hash/3e9f0fc9b2f89e043bc6233994dfcf76-Abstract.html}, year = {2019} } @article{liu2019roberta, author = {Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, Veselin}, journal = {ArXiv preprint}, title = {Roberta: A robustly optimized bert pretraining approach}, url = {https://arxiv.org/abs/1907.11692}, volume = {abs/1907.11692}, year = {2019} } @inproceedings{vig2020causal, author = {Vig, Jesse and Gehrmann, Sebastian and Belinkov, Yonatan and Qian, Sharon and Nevo, Daniel and Sakenis, Simas and Huang, Jason and Singer, Yaron and Shieber, Stuart}, booktitle = {NeurIPS}, title = {Causal mediation analysis for interpreting neural nlp: The case of gender bias}, year = {2020} } @inproceedings{de2021editing, address = {Online and Punta Cana, Dominican Republic}, author = {De Cao, Nicola and Aziz, Wilker and Titov, Ivan}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.522}, pages = {6491--6506}, publisher = {Association for Computational Linguistics}, title = {Editing Factual Knowledge in Language Models}, url = {https://aclanthology.org/2021.emnlp-main.522}, year = {2021} } @article{fedus2021switch, author = {Fedus, William and Zoph, Barret and Shazeer, Noam}, journal = {ArXiv preprint}, title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity}, url = {https://arxiv.org/abs/2101.03961}, volume = {abs/2101.03961}, year = {2021} } @inproceedings{lepikhin2020gshard, author = {Dmitry Lepikhin and HyoukJoong Lee and Yuanzhong Xu and Dehao Chen and Orhan Firat and Yanping Huang and Maxim Krikun and Noam Shazeer and Zhifeng Chen}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/LepikhinLXCFHKS21.bib}, booktitle = {9th International Conference on Learning Representations, {ICLR} 2021, Virtual Event, Austria, May 3-7, 2021}, publisher = {OpenReview.net}, timestamp = {Wed, 23 Jun 2021 01:00:00 +0200}, title = {GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding}, url = {https://openreview.net/forum?id=qrwe7XHTmYb}, year = {2021} } @inproceedings{he2021analyzing, address = {Online}, author = {He, Tianxing and Liu, Jun and Cho, Kyunghyun and Ott, Myle and Liu, Bing and Glass, James and Peng, Fuchun}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, doi = {10.18653/v1/2021.eacl-main.95}, pages = {1121--1133}, publisher = {Association for Computational Linguistics}, title = {Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models}, url = {https://aclanthology.org/2021.eacl-main.95}, year = {2021} } @inproceedings{d2019episodic, author = {Cyprien de Masson d'Autume and Sebastian Ruder and Lingpeng Kong and Dani Yogatama}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/dAutumeRKY19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {13122--13131}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Episodic Memory in Lifelong Language Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/f8d2e80c1458ea2501f98a2cafadb397-Abstract.html}, year = {2019} } @inproceedings{poerner2019bert, address = {Online}, author = {Poerner, Nina and Waltinger, Ulli and Sch{\""u}tze, Hinrich}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.71}, pages = {803--818}, publisher = {Association for Computational Linguistics}, title = {{E}-{BERT}: Efficient-Yet-Effective Entity Embeddings for {BERT}}, url = {https://aclanthology.org/2020.findings-emnlp.71}, year = {2020} } @inproceedings{elsahar2019t, address = {Miyazaki, Japan}, author = {Elsahar, Hady and Vougiouklis, Pavlos and Remaci, Arslen and Gravier, Christophe and Hare, Jonathon and Laforest, Frederique and Simperl, Elena}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {European Language Resources Association (ELRA)}, title = {{T}-{RE}x: A Large Scale Alignment of Natural Language with Knowledge Base Triples}, url = {https://aclanthology.org/L18-1544}, year = {2018} } @inproceedings{wolf-etal-2020-transformers, address = {Online}, author = {Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien and Delangue, Clement and Moi, Anthony and Cistac, Pierric and Rault, Tim and Louf, Remi and Funtowicz, Morgan and Davison, Joe and Shleifer, Sam and von Platen, Patrick and Ma, Clara and Jernite, Yacine and Plu, Julien and Xu, Canwen and Le Scao, Teven and Gugger, Sylvain and Drame, Mariama and Lhoest, Quentin and Rush, Alexander}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations}, doi = {10.18653/v1/2020.emnlp-demos.6}, pages = {38--45}, publisher = {Association for Computational Linguistics}, title = {Transformers: State-of-the-Art Natural Language Processing}, url = {https://aclanthology.org/2020.emnlp-demos.6}, year = {2020} } @inproceedings{zhang2021neural, address = {Online}, author = {Zhang, Zhiyuan and Ren, Xuancheng and Su, Qi and Sun, Xu and He, Bin}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.430}, pages = {5453--5466}, publisher = {Association for Computational Linguistics}, title = {Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects}, url = {https://aclanthology.org/2021.naacl-main.430}, year = {2021} } @inproceedings{thorne2018fever, address = {New Orleans, Louisiana}, author = {Thorne, James and Vlachos, Andreas and Christodoulopoulos, Christos and Mittal, Arpit}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1074}, pages = {809--819}, publisher = {Association for Computational Linguistics}, title = {{FEVER}: a Large-scale Dataset for Fact Extraction and {VER}ification}, url = {https://aclanthology.org/N18-1074}, year = {2018} } @article{Yao2021RefiningNN, author = {Huihan Yao and Ying Chen and Qinyuan Ye and Xisen Jin and Xiang Ren}, journal = {ArXiv preprint}, title = {Refining Neural Networks with Compositional Explanations}, url = {https://arxiv.org/abs/2103.10415}, volume = {abs/2103.10415}, year = {2021} } @inproceedings{fan2019eli5, address = {Florence, Italy}, author = {Fan, Angela and Jernite, Yacine and Perez, Ethan and Grangier, David and Weston, Jason and Auli, Michael}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1346}, pages = {3558--3567}, publisher = {Association for Computational Linguistics}, title = {{ELI}5: Long Form Question Answering}, url = {https://aclanthology.org/P19-1346}, year = {2019} } @inproceedings{hoffart2011robust, address = {Edinburgh, Scotland, UK.}, author = {Hoffart, Johannes and Yosef, Mohamed Amir and Bordino, Ilaria and F{\""u}rstenau, Hagen and Pinkal, Manfred and Spaniol, Marc and Taneva, Bilyana and Thater, Stefan and Weikum, Gerhard}, booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing}, pages = {782--792}, publisher = {Association for Computational Linguistics}, title = {Robust Disambiguation of Named Entities in Text}, url = {https://aclanthology.org/D11-1072}, year = {2011} } @article{guo2018robust, author = {Guo, Zhaochen and Barbosa, Denilson}, journal = {Semantic Web}, number = {4}, pages = {459--479}, publisher = {IOS Press}, title = {Robust named entity disambiguation with random walks}, volume = {9}, year = {2018} } @inproceedings{levy2017zero, address = {Vancouver, Canada}, author = {Levy, Omer and Seo, Minjoon and Choi, Eunsol and Zettlemoyer, Luke}, booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)}, doi = {10.18653/v1/K17-1034}, pages = {333--342}, publisher = {Association for Computational Linguistics}, title = {Zero-Shot Relation Extraction via Reading Comprehension}, url = {https://aclanthology.org/K17-1034}, year = {2017} } @article{hu2021lora, author = {Hu, Edward J and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu}, journal = {ArXiv preprint}, title = {LoRA: Low-Rank Adaptation of Large Language Models}, url = {https://arxiv.org/abs/2106.09685}, volume = {abs/2106.09685}, year = {2021} } @inproceedings{lewis2020question, address = {Online}, author = {Lewis, Patrick and Stenetorp, Pontus and Riedel, Sebastian}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, doi = {10.18653/v1/2021.eacl-main.86}, pages = {1000--1008}, publisher = {Association for Computational Linguistics}, title = {Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets}, url = {https://aclanthology.org/2021.eacl-main.86}, year = {2021} } @article{lewis2021paq, address = {Cambridge, MA}, author = {Lewis, Patrick and Wu, Yuxiang and Liu, Linqing and Minervini, Pasquale and K{\""u}ttler, Heinrich and Piktus, Aleksandra and Stenetorp, Pontus and Riedel, Sebastian}, doi = {10.1162/tacl_a_00415}, journal = {Transactions of the Association for Computational Linguistics}, pages = {1098--1115}, publisher = {MIT Press}, title = {{PAQ}: 65 Million Probably-Asked Questions and What You Can Do With Them}, url = {https://aclanthology.org/2021.tacl-1.65}, volume = {9}, year = {2021} } @article{choi2021decontextualization, address = {Cambridge, MA}, author = {Choi, Eunsol and Palomaki, Jennimaria and Lamm, Matthew and Kwiatkowski, Tom and Das, Dipanjan and Collins, Michael}, doi = {10.1162/tacl_a_00377}, journal = {Transactions of the Association for Computational Linguistics}, pages = {447--461}, publisher = {MIT Press}, title = {Decontextualization: Making Sentences Stand-Alone}, url = {https://aclanthology.org/2021.tacl-1.27}, volume = {9}, year = {2021} } @inproceedings{sang2003introduction, author = {Tjong Kim Sang, Erik F.}, booktitle = {{COLING}-02: The 6th Conference on Natural Language Learning 2002 ({C}o{NLL}-2002)}, title = {Introduction to the {C}o{NLL}-2002 Shared Task: Language-Independent Named Entity Recognition}, url = {https://aclanthology.org/W02-2024}, year = {2002} } @inproceedings{xu2021beyond, address = {Dublin, Ireland}, author = {Xu, Jing and Szlam, Arthur and Weston, Jason}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.356}, pages = {5180--5197}, publisher = {Association for Computational Linguistics}, title = {Beyond Goldfish Memory: Long-Term Open-Domain Conversation}, url = {https://aclanthology.org/2022.acl-long.356}, year = {2022} } @inproceedings{komeili2021internet, address = {Dublin, Ireland}, author = {Komeili, Mojtaba and Shuster, Kurt and Weston, Jason}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.579}, pages = {8460--8478}, publisher = {Association for Computational Linguistics}, title = {{I}nternet-Augmented Dialogue Generation}, url = {https://aclanthology.org/2022.acl-long.579}, year = {2022} } @inproceedings{bang2021rainbow, author = {Bang, Jihwan and Kim, Heesu and Yoo, YoungJoon and Ha, Jung-Woo and Choi, Jonghyun}, booktitle = {CVPR}, title = {Rainbow Memory: Continual Learning with a Memory of Diverse Samples}, year = {2021} } @inproceedings{prabhu2020gdumb, author = {Prabhu, Ameya and Torr, Philip HS and Dokania, Puneet K}, booktitle = {ECCV}, title = {Gdumb: A simple approach that questions our progress in continual learning}, year = {2020} } @inproceedings{chuang2020lifelong, address = {Online}, author = {Chuang, Yung-Sung and Su, Shang-Yu and Chen, Yun-Nung}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.233}, pages = {2914--2924}, publisher = {Association for Computational Linguistics}, title = {Lifelong Language Knowledge Distillation}, url = {https://aclanthology.org/2020.emnlp-main.233}, year = {2020} } @inproceedings{TiedemannThottingal:EAMT2020, address = {Lisboa, Portugal}, author = {Tiedemann, J{\""o}rg and Thottingal, Santhosh}, booktitle = {Proceedings of the 22nd Annual Conference of the European Association for Machine Translation}, pages = {479--480}, publisher = {European Association for Machine Translation}, title = {{OPUS}-{MT} {--} Building open translation services for the World}, url = {https://aclanthology.org/2020.eamt-1.61}, year = {2020} } @inproceedings{longpre2021entity, address = {Online and Punta Cana, Dominican Republic}, author = {Longpre, Shayne and Perisetla, Kartik and Chen, Anthony and Ramesh, Nikhil and DuBois, Chris and Singh, Sameer}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.565}, pages = {7052--7063}, publisher = {Association for Computational Linguistics}, title = {Entity-Based Knowledge Conflicts in Question Answering}, url = {https://aclanthology.org/2021.emnlp-main.565}, year = {2021} } @inproceedings{wang2021can, address = {Online}, author = {Wang, Cunxiang and Liu, Pai and Zhang, Yue}, booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, doi = {10.18653/v1/2021.acl-long.251}, pages = {3241--3251}, publisher = {Association for Computational Linguistics}, title = {Can Generative Pre-trained Language Models Serve As Knowledge Bases for Closed-book {QA}?}, url = {https://aclanthology.org/2021.acl-long.251}, year = {2021} } @inproceedings{zhou2020pre, author = {Wangchunshu Zhou and Dong{-}Ho Lee and Ravi Kiran Selvam and Seyeon Lee and Xiang Ren}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ZhouLSL021.bib}, booktitle = {9th International Conference on Learning Representations, {ICLR} 2021, Virtual Event, Austria, May 3-7, 2021}, publisher = {OpenReview.net}, timestamp = {Wed, 23 Jun 2021 01:00:00 +0200}, title = {Pre-training Text-to-Text Transformers for Concept-centric Common Sense}, url = {https://openreview.net/forum?id=3k20LAiHYL2}, year = {2021} } @article{li2021efficient, author = {Li, Yanyang and Lin, Ye and Xiao, Tong and Zhu, Jingbo}, journal = {ArXiv preprint}, title = {An efficient transformer decoder with compressed sub-layers}, url = {https://arxiv.org/abs/2101.00542}, volume = {abs/2101.00542}, year = {2021} } @inproceedings{lee2021deduplicating, address = {Dublin, Ireland}, author = {Lee, Katherine and Ippolito, Daphne and Nystrom, Andrew and Zhang, Chiyuan and Eck, Douglas and Callison-Burch, Chris and Carlini, Nicholas}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.577}, pages = {8424--8445}, publisher = {Association for Computational Linguistics}, title = {Deduplicating Training Data Makes Language Models Better}, url = {https://aclanthology.org/2022.acl-long.577}, year = {2022} } @inproceedings{autoprompt:emnlp20, address = {Online}, author = {Shin, Taylor and Razeghi, Yasaman and Logan IV, Robert L. and Wallace, Eric and Singh, Sameer}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.346}, pages = {4222--4235}, publisher = {Association for Computational Linguistics}, title = {{A}uto{P}rompt: {E}liciting {K}nowledge from {L}anguage {M}odels with {A}utomatically {G}enerated {P}rompts}, url = {https://aclanthology.org/2020.emnlp-main.346}, year = {2020} } @inproceedings{gururangan2020don, address = {Online}, author = {Gururangan, Suchin and Marasovi{\'c}, Ana and Swayamdipta, Swabha and Lo, Kyle and Beltagy, Iz and Downey, Doug and Smith, Noah A.}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.740}, pages = {8342--8360}, publisher = {Association for Computational Linguistics}, title = {Don{'}t Stop Pretraining: Adapt Language Models to Domains and Tasks}, url = {https://aclanthology.org/2020.acl-main.740}, year = {2020} } @inproceedings{yoon2017lifelong, author = {Jaehong Yoon and Eunho Yang and Jeongtae Lee and Sung Ju Hwang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/YoonYLH18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Lifelong Learning with Dynamically Expandable Networks}, url = {https://openreview.net/forum?id=Sk7KsfW0-}, year = {2018} } @inproceedings{zhang2021situatedqa, address = {Online and Punta Cana, Dominican Republic}, author = {Zhang, Michael and Choi, Eunsol}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.586}, pages = {7371--7387}, publisher = {Association for Computational Linguistics}, title = {{S}ituated{QA}: Incorporating Extra-Linguistic Contexts into {QA}}, url = {https://aclanthology.org/2021.emnlp-main.586}, year = {2021} } @article{dhingra2021time, address = {Cambridge, MA}, author = {Dhingra, Bhuwan and Cole, Jeremy R. and Eisenschlos, Julian Martin and Gillick, Daniel and Eisenstein, Jacob and Cohen, William W.}, doi = {10.1162/tacl_a_00459}, journal = {Transactions of the Association for Computational Linguistics}, pages = {257--273}, publisher = {MIT Press}, title = {Time-Aware Language Models as Temporal Knowledge Bases}, url = {https://aclanthology.org/2022.tacl-1.15}, volume = {10}, year = {2022} } @inproceedings{Dai2021KnowledgeNI, address = {Dublin, Ireland}, author = {Dai, Damai and Dong, Li and Hao, Yaru and Sui, Zhifang and Chang, Baobao and Wei, Furu}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.581}, pages = {8493--8502}, publisher = {Association for Computational Linguistics}, title = {Knowledge Neurons in Pretrained Transformers}, url = {https://aclanthology.org/2022.acl-long.581}, year = {2022} } @article{lazaridou2021pitfalls, author = {Lazaridou, Angeliki and Kuncoro, Adhiguna and Gribovskaya, Elena and Agrawal, Devang and Liska, Adam and Terzi, Tayfun and Gimenez, Mai and d'Autume, Cyprien de Masson and Ruder, Sebastian and Yogatama, Dani and others}, journal = {ArXiv preprint}, title = {Pitfalls of Static Language Modelling}, url = {https://arxiv.org/abs/2102.01951}, volume = {abs/2102.01951}, year = {2021} } @inproceedings{jin2021lifelong, address = {virtual+Dublin}, author = {Jin, Xisen and Zhang, Dejiao and Zhu, Henghui and Xiao, Wei and Li, Shang-Wen and Wei, Xiaokai and Arnold, Andrew and Ren, Xiang}, booktitle = {Proceedings of BigScience Episode {\#}5 -- Workshop on Challenges {\&} Perspectives in Creating Large Language Models}, doi = {10.18653/v1/2022.bigscience-1.1}, pages = {1--16}, publisher = {Association for Computational Linguistics}, title = {Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora}, url = {https://aclanthology.org/2022.bigscience-1.1}, year = {2022} } ","'@article{Acharya2020AnAO, author = {A. Acharya and Kartik Talamadupula and Mark A. Finlayson}, journal = {ArXiv preprint}, title = {An Atlas of Cultural Commonsense for Machine Reasoning}, url = {https://arxiv.org/abs/2009.05664}, volume = {abs/2009.05664}, year = {2020} } @book{Aho:72, address = {Englewood Cliffs, NJ}, author = {Alfred V. Aho and Jeffrey D. Ullman}, publisher = {Prentice-Hall}, title = {The Theory of Parsing, Translation and Compiling}, volume = {1}, year = {1972} } @article{Nottingham2023Embodied, author = {Kolby Nottingham and Prithviraj Ammanabrolu and Alane Suhr and Yejin Choi and Hannaneh Hajishirzi and Sameer Singh and Roy Fox}, journal = {ArXiv preprint}, title = {Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling}, url = {https://arxiv.org/abs/2301.12050}, volume = {abs/2301.12050}, year = {2023} } @article{Song2022LLMPlannerFG, author = {Chan Hee Song and Jiaman Wu and Clay Washington and Brian M. Sadler and Wei-Lun Chao and Yu Su}, journal = {ArXiv preprint}, title = {LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models}, url = {https://arxiv.org/abs/2212.04088}, volume = {abs/2212.04088}, year = {2022} } @article{Huang2022LanguageMA, author = {Wenlong Huang and P. Abbeel and Deepak Pathak and Igor Mordatch}, journal = {ArXiv preprint}, title = {Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents}, url = {https://arxiv.org/abs/2201.07207}, volume = {abs/2201.07207}, year = {2022} } @article{Lin2022OnGP, author = {Bill Yuchen Lin and Chengsong Huang and Qianchu Liu and Wenda Gu and Sam Sommerer and Xiang Ren}, journal = {ArXiv preprint}, title = {On Grounded Planning for Embodied Tasks with Language Models}, url = {https://arxiv.org/abs/2209.00465}, volume = {abs/2209.00465}, year = {2022} } @inproceedings{saycan, author = {Michael Ahn and Anthony Brohan and Noah Brown and Yevgen Chebotar and Omar Cortes and Byron David and Chelsea Finn and Keerthana Gopalakrishnan and Karol Hausman and Alexander Herzog and Daniel Ho and Jasmine Hsu and Julian Ibarz and Brian Ichter and Alex Irpan and Eric Jang and Rosario Jauregui Ruano and Kyle Jeffrey and Sally Jesmonth and Nikhil Jayant Joshi and Ryan C. Julian and Dmitry Kalashnikov and Yuheng Kuang and Kuang-Huei Lee and Sergey Levine and Yao Lu and Linda Luu and Carolina Parada and Peter Pastor and Jornell Quiambao and Kanishka Rao and Jarek Rettinghouse and Diego M Reyes and Pierre Sermanet and Nicolas Sievers and Clayton Tan and Alexander Toshev and Vincent Vanhoucke and F. Xia and Ted Xiao and Peng Xu and Sichun Xu and Mengyuan Yan}, booktitle = {Conference on Robot Learning}, title = {Do As I Can, Not As I Say: Grounding Language in Robotic Affordances}, year = {2022} } @inproceedings{calm, address = {Online}, author = {Yao, Shunyu and Rao, Rohan and Hausknecht, Matthew and Narasimhan, Karthik}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.704}, pages = {8736--8754}, publisher = {Association for Computational Linguistics}, title = {Keep {CALM} and Explore: Language Models for Action Generation in Text-based Games}, url = {https://aclanthology.org/2020.emnlp-main.704}, year = {2020} } @book{Kahneman2011ThinkingFA, author = {Daniel Kahneman}, title = {Thinking, Fast and Slow}, year = {2011} } @inproceedings{openie, address = {Beijing, China}, author = {Angeli, Gabor and Johnson Premkumar, Melvin Jose and Manning, Christopher D.}, booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, doi = {10.3115/v1/P15-1034}, pages = {344--354}, publisher = {Association for Computational Linguistics}, title = {Leveraging Linguistic Structure For Open Domain Information Extraction}, url = {https://aclanthology.org/P15-1034}, year = {2015} } @inproceedings{kga2c, author = {Prithviraj Ammanabrolu and Matthew J. Hausknecht}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/AmmanabroluH20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Graph Constrained Reinforcement Learning for Natural Language Action Spaces}, url = {https://openreview.net/forum?id=B1x6w0EtwH}, year = {2020} } @inproceedings{twc, author = {Keerthiram Murugesan and Mattia Atzeni and Pavan Kapanipathi and Pushkar Shukla and Sadhana Kumaravel and Gerald Tesauro and Kartik Talamadupula and Mrinmaya Sachan and Murray Campbell}, booktitle = {Thirty Fifth AAAI Conference on Artificial Intelligence}, title = {{Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines}}, year = {2021} } @article{Miech2021ThinkingFA, author = {Antoine Miech and Jean-Baptiste Alayrac and Ivan Laptev and Josef Sivic and Andrew Zisserman}, journal = {2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, pages = {9821-9831}, title = {Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers}, year = {2021} } @article{Chung2022ScalingIL, author = {Hyung Won Chung and Le Hou and S. Longpre and Barret Zoph and Yi Tay and William Fedus and Eric Li and Xuezhi Wang and Mostafa Dehghani and Siddhartha Brahma and Albert Webson and Shixiang Shane Gu and Zhuyun Dai and Mirac Suzgun and Xinyun Chen and Aakanksha Chowdhery and Dasha Valter and Sharan Narang and Gaurav Mishra and Adams Wei Yu and Vincent Zhao and Yanping Huang and Andrew M. Dai and Hongkun Yu and Slav Petrov and Ed Huai-hsin Chi and Jeff Dean and Jacob Devlin and Adam Roberts and Denny Zhou and Quoc V. Le and Jason Wei}, journal = {ArXiv preprint}, title = {Scaling Instruction-Finetuned Language Models}, url = {https://arxiv.org/abs/2210.11416}, volume = {abs/2210.11416}, year = {2022} } @article{Chen2019DeepRN, author = {Di Chen and Yiwei Bai and Wenting Zhao and Sebastian Ament and J. Gregoire and Carla P. Gomes}, journal = {ArXiv preprint}, title = {Deep Reasoning Networks: Thinking Fast and Slow}, url = {https://arxiv.org/abs/1906.00855}, volume = {abs/1906.00855}, year = {2019} } @inproceedings{Ganapini2021ThinkingFA, author = {M. B. Ganapini and Murray Campbell and F. Fabiano and L. Horesh and Jonathan Lenchner and Andrea Loreggia and Nicholas Mattei and Francesca Rossi and Biplav Srivastava and Kristen Brent Venable}, booktitle = {International Conference on Machine Learning, Optimization, and Data Science}, title = {Thinking Fast and Slow in AI: the Role of Metacognition}, year = {2021} } @inproceedings{Booch2020ThinkingFA, author = {Grady Booch and F. Fabiano and L. Horesh and Kiran Kate and Jonathan Lenchner and Nick Linck and Andrea Loreggia and Keerthiram Murugesan and Nicholas Mattei and Francesca Rossi and Biplav Srivastava}, booktitle = {AAAI Conference on Artificial Intelligence}, title = {Thinking Fast and Slow in AI}, year = {2020} } @inproceedings{Anthony2017ThinkingFA, author = {Thomas Anthony and Zheng Tian and David Barber}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/AnthonyTB17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {5360--5370}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Thinking Fast and Slow with Deep Learning and Tree Search}, url = {https://proceedings.neurips.cc/paper/2017/hash/d8e1344e27a5b08cdfd5d027d9b8d6de-Abstract.html}, year = {2017} } @inproceedings{tbc, address = {Online}, author = {Ammanabrolu, Prithviraj and Urbanek, Jack and Li, Margaret and Szlam, Arthur and Rockt{\""a}schel, Tim and Weston, Jason}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.64}, pages = {807--833}, publisher = {Association for Computational Linguistics}, title = {How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds}, url = {https://aclanthology.org/2021.naacl-main.64}, year = {2021} } @inproceedings{dt, author = {Lili Chen and Kevin Lu and Aravind Rajeswaran and Kimin Lee and Aditya Grover and Michael Laskin and P. Abbeel and A. Srinivas and Igor Mordatch}, booktitle = {Neural Information Processing Systems}, title = {Decision Transformer: Reinforcement Learning via Sequence Modeling}, year = {2021} } @article{Wang2023DescribeEP, author = {Zihao Wang and Shaofei Cai and Anji Liu and Xiaojian Ma and Yitao Liang}, journal = {ArXiv preprint}, title = {Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents}, url = {https://arxiv.org/abs/2302.01560}, volume = {abs/2302.01560}, year = {2023} } @article{Shridhar2020ALFWorldAT, author = {Mohit Shridhar and Xingdi Yuan and Marc-Alexandre C{\^o}t{\'e} and Yonatan Bisk and Adam Trischler and Matthew J. Hausknecht}, journal = {ArXiv preprint}, title = {ALFWorld: Aligning Text and Embodied Environments for Interactive Learning}, url = {https://arxiv.org/abs/2010.03768}, volume = {abs/2010.03768}, year = {2020} } @article{ai2thor, author = {Eric Kolve and Roozbeh Mottaghi and Winson Han and Eli VanderBilt and Luca Weihs and Alvaro Herrasti and Daniel Gordon and Yuke Zhu and Abhinav Gupta and Ali Farhadi}, journal = {arXiv}, title = {{AI2-THOR: An Interactive 3D Environment for Visual AI}}, year = {2017} } @inproceedings{tw, author = {Marc-Alexandre C{\^o}t{\'e} and {\'A}kos K{\'a}d{\'a}r and Xingdi Yuan and Ben A. Kybartas and Tavian Barnes and Emery Fine and James Moore and Matthew J. Hausknecht and Layla El Asri and Mahmoud Adada and Wendy Tay and Adam Trischler}, booktitle = {CGW@IJCAI}, title = {TextWorld: A Learning Environment for Text-based Games}, year = {2018} } @article{wason1974dual, author = {Wason, Peter C and Evans, J St BT}, journal = {Cognition}, number = {2}, pages = {141--154}, publisher = {Elsevier}, title = {Dual processes in reasoning?}, volume = {3}, year = {1974} } @article{react, author = {Shunyu Yao and Jeffrey Zhao and Dian Yu and Nan Du and Izhak Shafran and Karthik Narasimhan and Yuan Cao}, journal = {ArXiv preprint}, title = {ReAct: Synergizing Reasoning and Acting in Language Models}, url = {https://arxiv.org/abs/2210.03629}, volume = {abs/2210.03629}, year = {2022} } @article{reflexion, author = {Noah Shinn and Beck Labash and Ashwin Gopinath}, journal = {ArXiv preprint}, title = {Reflexion: an autonomous agent with dynamic memory and self-reflection}, url = {https://arxiv.org/abs/2303.11366}, volume = {abs/2303.11366}, year = {2023} } @inproceedings{seq2seq, author = {Ilya Sutskever and Oriol Vinyals and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SutskeverVL14.bib}, booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada}, editor = {Zoubin Ghahramani and Max Welling and Corinna Cortes and Neil D. Lawrence and Kilian Q. Weinberger}, pages = {3104--3112}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Sequence to Sequence Learning with Neural Networks}, url = {https://proceedings.neurips.cc/paper/2014/hash/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html}, year = {2014} } @inproceedings{Torabi2018BehavioralCF, author = {Faraz Torabi and Garrett Warnell and Peter Stone}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/TorabiWS18.bib}, booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm, Sweden}, doi = {10.24963/ijcai.2018/687}, editor = {J{\'{e}}r{\^{o}}me Lang}, pages = {4950--4957}, publisher = {ijcai.org}, timestamp = {Tue, 20 Aug 2019 01:00:00 +0200}, title = {Behavioral Cloning from Observation}, url = {https://doi.org/10.24963/ijcai.2018/687}, year = {2018} } @inproceedings{drrn, address = {Berlin, Germany}, author = {He, Ji and Chen, Jianshu and He, Xiaodong and Gao, Jianfeng and Li, Lihong and Deng, Li and Ostendorf, Mari}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1153}, pages = {1621--1630}, publisher = {Association for Computational Linguistics}, title = {Deep Reinforcement Learning with a Natural Language Action Space}, url = {https://aclanthology.org/P16-1153}, year = {2016} } @article{Reed2022AGA, author = {Scott Reed and Konrad Zolna and Emilio Parisotto and Sergio Gomez Colmenarejo and Alexander Novikov and Gabriel Barth-Maron and Mai Gimenez and Yury Sulsky and Jackie Kay and Jost Tobias Springenberg and Tom Eccles and Jake Bruce and Ali Razavi and Ashley D. Edwards and Nicolas Manfred Otto Heess and Yutian Chen and Raia Hadsell and Oriol Vinyals and Mahyar Bordbar and Nando de Freitas}, journal = {ArXiv preprint}, title = {A Generalist Agent}, url = {https://arxiv.org/abs/2205.06175}, volume = {abs/2205.06175}, year = {2022} } @article{Bubeck2023SparksOA, author = {S{\'e}bastien Bubeck and Varun Chandrasekaran and Ronen Eldan and John A. Gehrke and Eric Horvitz and Ece Kamar and Peter Lee and Yin Tat Lee and Yuan-Fang Li and Scott M. Lundberg and Harsha Nori and Hamid Palangi and Marco Tulio Ribeiro and Yi Zhang}, journal = {ArXiv preprint}, title = {Sparks of Artificial General Intelligence: Early experiments with GPT-4}, url = {https://arxiv.org/abs/2303.12712}, volume = {abs/2303.12712}, year = {2023} } @inproceedings{sw, author = {Ruoyao Wang and Peter Alexander Jansen and Marc-Alexandre C{\^o}t{\'e} and Prithviraj Ammanabrolu}, booktitle = {Conference on Empirical Methods in Natural Language Processing}, title = {ScienceWorld: Is your Agent Smarter than a 5th Grader?}, year = {2022} } @inproceedings{Lewis2020RetrievalAugmentedGF, author = {Patrick S. H. Lewis and Ethan Perez and Aleksandra Piktus and Fabio Petroni and Vladimir Karpukhin and Naman Goyal and Heinrich K{\""{u}}ttler and Mike Lewis and Wen{-}tau Yih and Tim Rockt{\""{a}}schel and Sebastian Riedel and Douwe Kiela}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/LewisPPPKGKLYR020.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks}, url = {https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html}, year = {2020} } @inproceedings{Guu2020REALMRL, author = {Kelvin Guu and Kenton Lee and Zora Tung and Panupong Pasupat and Ming{-}Wei Chang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/GuuLTPC20.bib}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, pages = {3929--3938}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, title = {Retrieval Augmented Language Model Pre-Training}, url = {http://proceedings.mlr.press/v119/guu20a.html}, volume = {119}, year = {2020} } @inproceedings{Lin2021DifferentiableOC, address = {Online}, author = {Lin, Bill Yuchen and Sun, Haitian and Dhingra, Bhuwan and Zaheer, Manzil and Ren, Xiang and Cohen, William}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.366}, pages = {4611--4625}, publisher = {Association for Computational Linguistics}, title = {Differentiable Open-Ended Commonsense Reasoning}, url = {https://aclanthology.org/2021.naacl-main.366}, year = {2021} } @article{InstructGPT, author = {Long Ouyang and Jeff Wu and Xu Jiang and Diogo Almeida and Carroll L. Wainwright and Pamela Mishkin and Chong Zhang and Sandhini Agarwal and Katarina Slama and Alex Ray and John Schulman and Jacob Hilton and Fraser Kelton and Luke E. Miller and Maddie Simens and Amanda Askell and Peter Welinder and Paul Francis Christiano and Jan Leike and Ryan J. Lowe}, journal = {ArXiv preprint}, title = {Training language models to follow instructions with human feedback}, url = {https://arxiv.org/abs/2203.02155}, volume = {abs/2203.02155}, year = {2022} } @article{bigbench, author = {Aarohi Srivastava and Abhinav Rastogi and Abhishek B Rao and Abu Awal Md Shoeb and Abubakar Abid and Adam Fisch and Adam R. Brown and Adam Santoro and Aditya Gupta and Adri{\`a} Garriga-Alonso and Agnieszka Kluska and Aitor Lewkowycz and Akshat Agarwal and Alethea Power and Alex Ray and Alex Warstadt and Alexander W. Kocurek and Ali Safaya and Ali Tazarv and Alice Xiang and Alicia Parrish and Allen Nie and Aman Hussain and Amanda Askell and Amanda Dsouza and Ameet Annasaheb Rahane and Anantharaman S. Iyer and Anders Johan Andreassen and Andrea Santilli and Andreas Stuhlmuller and Andrew M. Dai and Andrew D. La and Andrew Kyle Lampinen and Andy Zou and Angela Jiang and Angelica Chen and Anh Vuong and Animesh Gupta and Anna Gottardi and Antonio Norelli and Anu Venkatesh and Arash Gholamidavoodi and Arfa Tabassum and Arul Menezes and Arun Kirubarajan and Asher Mullokandov and Ashish Sabharwal and Austin Herrick and Avia Efrat and Aykut Erdem and Ayla Karakacs and Bridget R. Roberts and Bao Sheng Loe and Barret Zoph and Bartlomiej Bojanowski and Batuhan Ozyurt and Behnam Hedayatnia and Behnam Neyshabur and Benjamin Inden and Benno Stein and Berk Ekmekci and Bill Yuchen Lin and Blake Stephen Howald and Cameron Diao and Cameron Dour and Catherine Stinson and Cedrick Argueta and C'esar Ferri Ram'irez and Chandan Singh and Charles Rathkopf and Chenlin Meng and Chitta Baral and Chiyu Wu and Chris Callison-Burch and Chris Waites and Christian Voigt and Christopher D. Manning and Christopher Potts and Cindy Tatiana Ramirez and Clara Rivera and Clemencia Siro and Colin Raffel and Courtney Ashcraft and Cristina Garbacea and Damien Sileo and Daniel H Garrette and Dan Hendrycks and Dan Kilman and Dan Roth and Daniel Freeman and Daniel Khashabi and Daniel Levy and Daniel Gonz'alez and Danny Hernandez and Danqi Chen and Daphne Ippolito and Dar Gilboa and David Dohan and D. Drakard and David Jurgens and Debajyoti Datta and Deep Ganguli and Denis Emelin and Denis Kleyko and Deniz Yuret and Derek Chen and Derek Tam and Dieuwke Hupkes and Diganta Misra and Dilyar Buzan and Dimitri Coelho Mollo and Diyi Yang and Dong-Ho Lee and Ekaterina Shutova and Ekin Dogus Cubuk and Elad Segal and Eleanor Hagerman and Elizabeth Barnes and Elizabeth P. Donoway and Ellie Pavlick and Emanuele Rodol{\`a} and Emma FC Lam and Eric Chu and Eric Tang and Erkut Erdem and Ernie Chang and Ethan A. Chi and Ethan Dyer and Ethan Jerzak and Ethan Kim and Eunice Engefu Manyasi and Evgenii Zheltonozhskii and Fan Xia and Fatemeh Siar and Fernando Mart'inez-Plumed and Francesca Happ'e and François Chollet and Frieda Rong and Gaurav Mishra and Genta Indra Winata and Gerard de Melo and Germ{\'a}n Kruszewski and Giambattista Parascandolo and Giorgio Mariani and Gloria Wang and Gonzalo Jaimovitch-L'opez and Gregor Betz and Guy Gur-Ari and Hana Galijasevic and Han Sol Kim and Hannah Rashkin and Hanna Hajishirzi and Harsh Mehta and Hayden Bogar and Henry Shevlin and Hinrich Sch{\""u}tze and Hiromu Yakura and Hongming Zhang and Hubert Wong and Ian Aik-Soon Ng and Isaac Noble and Jaap Jumelet and Jack Geissinger and John Kernion and Jacob Hilton and Jaehoon Lee and Jaime Fern{\'a}ndez Fisac and J. Brooker Simon and James Koppel and James Zheng and James Zou and Jan Koco'n and Jana Thompson and Jared Kaplan and Jarema Radom and Jascha Narain Sohl-Dickstein and Jason Phang and Jason Wei and Jason Yosinski and Jekaterina Novikova and Jelle Bosscher and Jenni Marsh and Jeremy Kim and Jeroen Taal and Jesse Engel and Jesujoba Oluwadara Alabi and Jiacheng Xu and Jiaming Song and Jillian Tang and Jane W Waweru and John Burden and John Miller and John U. Balis and Jonathan Berant and Jorg Frohberg and Jos Rozen and Jos{\'e} Hern{\'a}ndez-Orallo and Joseph Boudeman and Joseph Jones and Joshua B. Tenenbaum and Joshua S. Rule and Joyce Chua and Kamil Kanclerz and Karen Livescu and Karl Krauth and Karthik Gopalakrishnan and Katerina Ignatyeva and Katja Markert and Kaustubh D. Dhole and Kevin Gimpel and Kevin Ochieng’ Omondi and Kory Wallace Mathewson and Kristen Chiafullo and Ksenia Shkaruta and Kumar Shridhar and Kyle McDonell and Kyle Richardson and Laria Reynolds and Leo Gao and Li Zhang and Liam Dugan and Lianhui Qin and Lidia Contreras-Ochando and Louis-Philippe Morency and Luca Moschella and Luca Lam and Lucy Noble and Ludwig Schmidt and Luheng He and Luis Oliveros Col'on and Luke Metz and Lutfi Kerem cSenel and Maarten Bosma and Maarten Sap and Maartje ter Hoeve and Madotto Andrea and Maheen Saleem Farooqi and Manaal Faruqui and Mantas Mazeika and Marco Baturan and Marco Marelli and Marco Maru and M Quintana and Marie Tolkiehn and Mario Giulianelli and Martha Lewis and Martin Potthast and Matthew Leavitt and Matthias Hagen and M'aty'as Schubert and Medina Baitemirova and Melissa Arnaud and Melvin Andrew McElrath and Michael A. Yee and Michael Cohen and Mi Gu and Michael I. Ivanitskiy and Michael Starritt and Michael Strube and Michal Swkedrowski and Michele Bevilacqua and Michihiro Yasunaga and Mihir Kale and Mike Cain and Mimee Xu and Mirac Suzgun and Monica Tiwari and Mohit Bansal and Moin Aminnaseri and Mor Geva and Mozhdeh Gheini and T MukundVarma and Nanyun Peng and Nathan Chi and Nayeon Lee and Neta Gur-Ari Krakover and Nicholas Cameron and Nicholas S. Roberts and Nicholas Doiron and Nikita Nangia and Niklas Deckers and Niklas Muennighoff and Nitish Shirish Keskar and Niveditha Iyer and Noah Constant and Noah Fiedel and Nuan Wen and Oliver Zhang and Omar Agha and Omar Elbaghdadi and Omer Levy and Owain Evans and Pablo Antonio Moreno Casares and Parth Doshi and Pascale Fung and Paul Pu Liang and Paul Vicol and Pegah Alipoormolabashi and Peiyuan Liao and Percy Liang and Peter W. Chang and Peter Eckersley and Phu Mon Htut and Pi-Bei Hwang and P. Milkowski and Piyush S. Patil and Pouya Pezeshkpour and Priti Oli and Qiaozhu Mei and QING LYU and Qinlang Chen and Rabin Banjade and Rachel Etta Rudolph and Raefer Gabriel and Rahel Habacker and Ram'on Risco Delgado and Rapha{\""e}l Milli{\`e}re and Rhythm Garg and Richard Barnes and Rif A. Saurous and Riku Arakawa and Robbe Raymaekers and Robert Frank and Rohan Sikand and Roman Novak and Roman Sitelew and Ronan Le Bras and Rosanne Liu and Rowan Jacobs and Rui Zhang and Ruslan Salakhutdinov and Ryan Chi and Ryan Lee and Ryan Stovall and Ryan Teehan and Rylan Yang and Sahib J. Singh and Saif M. Mohammad and Sajant Anand and Sam Dillavou and Sam Shleifer and Sam Wiseman and Samuel Gruetter and Sam Bowman and Samuel S. Schoenholz and Sanghyun Han and Sanjeev Kwatra and Sarah A. Rous and Sarik Ghazarian and Sayan Ghosh and Sean Casey and Sebastian Bischoff and Sebastian Gehrmann and Sebastian Schuster and Sepideh Sadeghi and Shadi S. Hamdan and Sharon Zhou and Shashank Srivastava and Sherry Shi and Shikhar Singh and Shima Asaadi and Shixiang Shane Gu and Shubh Pachchigar and Shubham Toshniwal and Shyam Upadhyay and Shyamolima Debnath and Siamak Shakeri and Simon Thormeyer and Simone Melzi and Siva Reddy and Sneha Priscilla Makini and Soo-hwan Lee and Spencer Bradley Torene and Sriharsha Hatwar and Stanislas Dehaene and Stefan Divic and Stefano Ermon and Stella Rose Biderman and Stephanie C. Lin and Stephen Prasad and Steven T. Piantadosi and Stuart M. Shieber and Summer Misherghi and Svetlana Kiritchenko and Swaroop Mishra and Tal Linzen and Tal Schuster and Tao Li and Tao Yu and Tariq A. Ali and Tatsuo Hashimoto and Te-Lin Wu and Theo Desbordes and Theodore Rothschild and Thomas Phan and Tianle Wang and Tiberius Nkinyili and Timo Schick and T. N. Kornev and Timothy Telleen-Lawton and Titus Tunduny and Tobias Gerstenberg and Trenton Chang and Trishala Neeraj and Tushar Khot and Tyler O. Shultz and Uri Shaham and Vedant Misra and Vera Demberg and Victoria Nyamai and Vikas Raunak and Vinay Venkatesh Ramasesh and Vinay Uday Prabhu and Vishakh Padmakumar and Vivek Srikumar and William Fedus and William Saunders and William Zhang and W Vossen and Xiang Ren and Xiaoyu F Tong and Xinyi Wu and Xudong Shen and Yadollah Yaghoobzadeh and Yair Lakretz and Yang Song and Yasaman Bahri and Ye Ji Choi and Yichi Yang and Yiding Hao and Yifu Chen and Yonatan Belinkov and Yu Hou and Yu Hou and Yushi Bai and Zachary Seid and Zhao Xinran and Zhuoye Zhao and Zi Fu Wang and Zijie J. Wang and Zirui Wang and Ziyi Wu and Sahib Singh and Uri Shaham}, journal = {ArXiv preprint}, title = {Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models}, url = {https://arxiv.org/abs/2206.04615}, volume = {abs/2206.04615}, year = {2022} } @inproceedings{Mishra2021CrossTaskGV, address = {Dublin, Ireland}, author = {Mishra, Swaroop and Khashabi, Daniel and Baral, Chitta and Hajishirzi, Hannaneh}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.244}, pages = {3470--3487}, publisher = {Association for Computational Linguistics}, title = {Cross-Task Generalization via Natural Language Crowdsourcing Instructions}, url = {https://aclanthology.org/2022.acl-long.244}, year = {2022} } @inproceedings{mishra2021cross, address = {Dublin, Ireland}, author = {Mishra, Swaroop and Khashabi, Daniel and Baral, Chitta and Hajishirzi, Hannaneh}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.244}, pages = {3470--3487}, publisher = {Association for Computational Linguistics}, title = {Cross-Task Generalization via Natural Language Crowdsourcing Instructions}, url = {https://aclanthology.org/2022.acl-long.244}, year = {2022} } @article{Wang2022BenchmarkingGV, author = {Yizhong Wang and Swaroop Mishra and Pegah Alipoormolabashi and Yeganeh Kordi and Amirreza Mirzaei and A. Arunkumar and Arjun Ashok and Arut Selvan Dhanasekaran and Atharva Naik and David Stap and Eshaan Pathak and Giannis Karamanolakis and Haizhi Gary Lai and Ishan Purohit and Ishani Mondal and Jacob Anderson and Kirby Kuznia and Krima Doshi and Maitreya Patel and Kuntal Kumar Pal and M. Moradshahi and Mihir Parmar and Mirali Purohit and Neeraj Varshney and Phani Rohitha Kaza and Pulkit Verma and Ravsehaj Singh Puri and Rushang Karia and Shailaja Keyur Sampat and Savan Doshi and Siddharth Deepak Mishra and Sujan C. Reddy and Sumanta Patro and Tanay Dixit and Xu-dong Shen and Chitta Baral and Yejin Choi and Hannaneh Hajishirzi and Noah A. Smith and Daniel Khashabi}, journal = {ArXiv preprint}, title = {Benchmarking Generalization via In-Context Instructions on 1, 600+ Language Tasks}, url = {https://arxiv.org/abs/2204.07705}, volume = {abs/2204.07705}, year = {2022} } @inproceedings{Vu2020ExploringAP, address = {Online}, author = {Vu, Tu and Wang, Tong and Munkhdalai, Tsendsuren and Sordoni, Alessandro and Trischler, Adam and Mattarella-Micke, Andrew and Maji, Subhransu and Iyyer, Mohit}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.635}, pages = {7882--7926}, publisher = {Association for Computational Linguistics}, title = {Exploring and Predicting Transferability across {NLP} Tasks}, url = {https://aclanthology.org/2020.emnlp-main.635}, year = {2020} } @inproceedings{Lange2021ToSO, address = {Online and Punta Cana, Dominican Republic}, author = {Lange, Lukas and Str{\""o}tgen, Jannik and Adel, Heike and Klakow, Dietrich}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.689}, pages = {8744--8753}, publisher = {Association for Computational Linguistics}, title = {To Share or not to Share: {P}redicting Sets of Sources for Model Transfer Learning}, url = {https://aclanthology.org/2021.emnlp-main.689}, year = {2021} } @inproceedings{Padmakumar2022ExploringTR, address = {Seattle, United States}, author = {Padmakumar, Vishakh and Lausen, Leonard and Ballesteros, Miguel and Zha, Sheng and He, He and Karypis, George}, booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2022.naacl-main.183}, pages = {2542--2550}, publisher = {Association for Computational Linguistics}, title = {Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning}, url = {https://aclanthology.org/2022.naacl-main.183}, year = {2022} } @inproceedings{brown2020languages, author = {Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert{-}Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Language Models are Few-Shot Learners}, url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html}, year = {2020} } @inproceedings{Rubin2021LearningTR, address = {Seattle, United States}, author = {Rubin, Ohad and Herzig, Jonathan and Berant, Jonathan}, booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2022.naacl-main.191}, pages = {2655--2671}, publisher = {Association for Computational Linguistics}, title = {Learning To Retrieve Prompts for In-Context Learning}, url = {https://aclanthology.org/2022.naacl-main.191}, year = {2022} } @inproceedings{Wang2022TrainingDI, address = {Dublin, Ireland}, author = {Wang, Shuohang and Xu, Yichong and Fang, Yuwei and Liu, Yang and Sun, Siqi and Xu, Ruochen and Zhu, Chenguang and Zeng, Michael}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.226}, pages = {3170--3179}, publisher = {Association for Computational Linguistics}, title = {Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data}, url = {https://aclanthology.org/2022.acl-long.226}, year = {2022} } @misc{sanh2021t0, archiveprefix = {arXiv}, author = {Victor Sanh and Albert Webson and Colin Raffel and Stephen H. Bach and Lintang Sutawika and Zaid Alyafeai and Antoine Chaffin and Arnaud Stiegler and Teven Le Scao and Arun Raja and Manan Dey and M Saiful Bari and Canwen Xu and Urmish Thakker and Shanya Sharma Sharma and Eliza Szczechla and Taewoon Kim and Gunjan Chhablani and Nihal Nayak and Debajyoti Datta and Jonathan Chang and Mike Tian-Jian Jiang and Han Wang and Matteo Manica and Sheng Shen and Zheng Xin Yong and Harshit Pandey and Rachel Bawden and Thomas Wang and Trishala Neeraj and Jos Rozen and Abheesht Sharma and Andrea Santilli and Thibault Fevry and Jason Alan Fries and Ryan Teehan and Stella Biderman and Leo Gao and Tali Bers and Thomas Wolf and Alexander M. Rush}, eprint = {2110.08207}, primaryclass = {cs.LG}, title = {Multitask Prompted Training Enables Zero-Shot Task Generalization}, year = {2021} } @inproceedings{bach2022promptsource, address = {Dublin, Ireland}, author = {Bach, Stephen and Sanh, Victor and Yong, Zheng Xin and Webson, Albert and Raffel, Colin and Nayak, Nihal V. and Sharma, Abheesht and Kim, Taewoon and Bari, M Saiful and Fevry, Thibault and Alyafeai, Zaid and Dey, Manan and Santilli, Andrea and Sun, Zhiqing and Ben-david, Srulik and Xu, Canwen and Chhablani, Gunjan and Wang, Han and Fries, Jason and Al-shaibani, Maged and Sharma, Shanya and Thakker, Urmish and Almubarak, Khalid and Tang, Xiangru and Radev, Dragomir and Jiang, Mike Tian-jian and Rush, Alexander}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations}, doi = {10.18653/v1/2022.acl-demo.9}, pages = {93--104}, publisher = {Association for Computational Linguistics}, title = {{P}rompt{S}ource: An Integrated Development Environment and Repository for Natural Language Prompts}, url = {https://aclanthology.org/2022.acl-demo.9}, year = {2022} } @article{Jang2021TowardsCK, author = {Joel Jang and Seonghyeon Ye and Sohee Yang and Joongbo Shin and Janghoon Han and Gyeonghun Kim and Stanley Jungkyu Choi and Minjoon Seo}, journal = {ArXiv preprint}, title = {Towards Continual Knowledge Learning of Language Models}, url = {https://arxiv.org/abs/2110.03215}, volume = {abs/2110.03215}, year = {2021} } @article{Mitchell2021FastME, author = {Eric Mitchell and Charles Lin and Antoine Bosselut and Chelsea Finn and Christopher D. Manning}, journal = {ArXiv preprint}, title = {Fast Model Editing at Scale}, url = {https://arxiv.org/abs/2110.11309}, volume = {abs/2110.11309}, year = {2021} } @inproceedings{clif, address = {Punta Cana, Dominican Republic}, author = {Jin, Xisen and Lin, Bill Yuchen and Rostami, Mohammad and Ren, Xiang}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021}, doi = {10.18653/v1/2021.findings-emnlp.62}, pages = {714--729}, publisher = {Association for Computational Linguistics}, title = {Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning}, url = {https://aclanthology.org/2021.findings-emnlp.62}, year = {2021} } @inproceedings{Rolnick2019ExperienceRF, author = {David Rolnick and Arun Ahuja and Jonathan Schwarz and Timothy P. Lillicrap and Gregory Wayne}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/RolnickASLW19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {348--358}, timestamp = {Thu, 21 Jan 2021 15:15:19 +0100}, title = {Experience Replay for Continual Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Abstract.html}, year = {2019} } @inproceedings{Kawaguchi2020OrderedSA, author = {Kenji Kawaguchi and Haihao Lu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aistats/KawaguchiL20.bib}, booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics, {AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]}, editor = {Silvia Chiappa and Roberto Calandra}, pages = {669--679}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Mon, 29 Jun 2020 01:00:00 +0200}, title = {Ordered {SGD:} {A} New Stochastic Optimization Framework for Empirical Risk Minimization}, url = {http://proceedings.mlr.press/v108/kawaguchi20a.html}, volume = {108}, year = {2020} } @inproceedings{aribandi2022ext, author = {Vamsi Aribandi and Yi Tay and Tal Schuster and Jinfeng Rao and Huaixiu Steven Zheng and Sanket Vaibhav Mehta and Honglei Zhuang and Vinh Q. Tran and Dara Bahri and Jianmo Ni and Jai Gupta and Kai Hui and Sebastian Ruder and Donald Metzler}, booktitle = {International Conference on Learning Representations}, title = {ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning}, url = {https://openreview.net/forum?id=Vzh1BFUCiIX}, year = {2022} } @inproceedings{chen2022weighted, author = {Shuxiao Chen and Koby Crammer and Hangfeng He and Dan Roth and Weijie J Su}, booktitle = {International Conference on Learning Representations}, title = {Weighted Training for Cross-Task Learning}, url = {https://openreview.net/forum?id=ltM1RMZntpu}, year = {2022} } @article{Jiang2019AcceleratingDL, author = {Angela H. Jiang and Daniel L.-K. Wong and Giulio Zhou and David G. Andersen and Jeff Dean and Gregory R. Ganger and Gauri Joshi and Michael Kaminsky and Michael A. Kozuch and Zachary Chase Lipton and Padmanabhan Pillai}, journal = {ArXiv preprint}, title = {Accelerating Deep Learning by Focusing on the Biggest Losers}, url = {https://arxiv.org/abs/1910.00762}, volume = {abs/1910.00762}, year = {2019} } @inproceedings{Mirzadeh2020UnderstandingTR, author = {Seyed{-}Iman Mirzadeh and Mehrdad Farajtabar and Razvan Pascanu and Hassan Ghasemzadeh}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/MirzadehFPG20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Understanding the Role of Training Regimes in Continual Learning}, url = {https://proceedings.neurips.cc/paper/2020/hash/518a38cc9a0173d0b2dc088166981cf8-Abstract.html}, year = {2020} } @article{Parisi2019ContinualLL, author = {German Ignacio Parisi and Ronald Kemker and Jose L. Part and Christopher Kanan and Stefan Wermter}, journal = {Neural networks : the official journal of the International Neural Network Society}, pages = {54-71 }, title = {Continual Lifelong Learning with Neural Networks: A Review}, volume = {113}, year = {2019} } @inproceedings{OSAKA, author = {Massimo Caccia and Pau Rodr{\'{\i}}guez and Oleksiy Ostapenko and Fabrice Normandin and Min Lin and Lucas Page{-}Caccia and Issam Hadj Laradji and Irina Rish and Alexandre Lacoste and David V{\'{a}}zquez and Laurent Charlin}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/CacciaRONLPLRLV20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Online Fast Adaptation and Knowledge Accumulation {(OSAKA):} a New Approach to Continual Learning}, url = {https://proceedings.neurips.cc/paper/2020/hash/c0a271bc0ecb776a094786474322cb82-Abstract.html}, year = {2020} } @article{Aljundi2019OnlineCL, author = {Rahaf Aljundi and Lucas Caccia and Eugene Belilovsky and Massimo Caccia and Min Lin and Laurent Charlin and Tinne Tuytelaars}, journal = {ArXiv preprint}, title = {Online Continual Learning with Maximally Interfered Retrieval}, url = {https://arxiv.org/abs/1908.04742}, volume = {abs/1908.04742}, year = {2019} } @article{Wei2021FinetunedLM, author = {Jason Wei and Maarten Bosma and Vincent Zhao and Kelvin Guu and Adams Wei Yu and Brian Lester and Nan Du and Andrew M. Dai and Quoc V. Le}, journal = {ArXiv preprint}, title = {Finetuned Language Models Are Zero-Shot Learners}, url = {https://arxiv.org/abs/2109.01652}, volume = {abs/2109.01652}, year = {2021} } @article{ewc2017, author = {James Kirkpatrick and Razvan Pascanu and Neil C. Rabinowitz and Joel Veness and Guillaume Desjardins and Andrei A. Rusu and Kieran Milan and John Quan and Tiago Ramalho and Agnieszka Grabska-Barwinska and Demis Hassabis and Claudia Clopath and Dharshan Kumaran and Raia Hadsell}, journal = {Proceedings of the National Academy of Sciences}, pages = {3521 - 3526}, title = {Overcoming catastrophic forgetting in neural networks}, volume = {114}, year = {2017} } @inproceedings{ye-etal-2021-crossfit, address = {Online and Punta Cana, Dominican Republic}, author = {Ye, Qinyuan and Lin, Bill Yuchen and Ren, Xiang}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.572}, pages = {7163--7189}, publisher = {Association for Computational Linguistics}, title = {{C}ross{F}it: A Few-shot Learning Challenge for Cross-task Generalization in {NLP}}, url = {https://aclanthology.org/2021.emnlp-main.572}, year = {2021} } @article{Dunn2017SearchQAAN, author = {Matthew Dunn and Levent Sagun and Mike Higgins and V. Ugur G{\""u}ney and Volkan Cirik and Kyunghyun Cho}, journal = {ArXiv preprint}, title = {SearchQA: A New Q\&A Dataset Augmented with Context from a Search Engine}, url = {https://arxiv.org/abs/1704.05179}, volume = {abs/1704.05179}, year = {2017} } @inproceedings{Trischler2017NewsQAAM, address = {Vancouver, Canada}, author = {Trischler, Adam and Wang, Tong and Yuan, Xingdi and Harris, Justin and Sordoni, Alessandro and Bachman, Philip and Suleman, Kaheer}, booktitle = {Proceedings of the 2nd Workshop on Representation Learning for {NLP}}, doi = {10.18653/v1/W17-2623}, pages = {191--200}, publisher = {Association for Computational Linguistics}, title = {{N}ews{QA}: A Machine Comprehension Dataset}, url = {https://aclanthology.org/W17-2623}, year = {2017} } @inproceedings{Joshi2017TriviaQAAL, address = {Vancouver, Canada}, author = {Joshi, Mandar and Choi, Eunsol and Weld, Daniel and Zettlemoyer, Luke}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1147}, pages = {1601--1611}, publisher = {Association for Computational Linguistics}, title = {{T}rivia{QA}: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension}, url = {https://aclanthology.org/P17-1147}, year = {2017} } @inproceedings{fisch-etal-2019-mrqa, address = {Hong Kong, China}, author = {Fisch, Adam and Talmor, Alon and Jia, Robin and Seo, Minjoon and Choi, Eunsol and Chen, Danqi}, booktitle = {Proceedings of the 2nd Workshop on Machine Reading for Question Answering}, doi = {10.18653/v1/D19-5801}, pages = {1--13}, publisher = {Association for Computational Linguistics}, title = {{MRQA} 2019 Shared Task: Evaluating Generalization in Reading Comprehension}, url = {https://aclanthology.org/D19-5801}, year = {2019} } @article{anderson1984schema, author = {Anderson, Richard C and Pearson, P David}, journal = {Handbook of reading research}, pages = {255--291}, title = {A schema-theoretic view of basic processes in reading comprehension}, volume = {1}, year = {1984} } @inproceedings{Anderson2016SPICESP, author = {Anderson, Peter and Fernando, Basura and Johnson, Mark and Gould, Stephen}, booktitle = {European Conference on Computer Vision}, organization = {Springer}, pages = {382--398}, title = {Spice: Semantic propositional image caption evaluation}, year = {2016} } @article{Ando2005, acmid = {1194905}, author = {Ando, Rie Kubota and Zhang, Tong}, issn = {1532-4435}, issue_date = {12/1/2005}, journal = {Journal of Machine Learning Research}, numpages = {37}, pages = {1817--1853}, publisher = {JMLR.org}, title = {A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data}, volume = {6}, year = {2005} } @inproceedings{andrew2007scalable, author = {Andrew, Galen and Gao, Jianfeng}, booktitle = {ICML}, pages = {33--40}, title = {Scalable training of {L1}-regularized log-linear models}, year = {2007} } @inproceedings{annervaz2018learningbd, address = {New Orleans, Louisiana}, author = {K M, Annervaz and Basu Roy Chowdhury, Somnath and Dukkipati, Ambedkar}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1029}, pages = {313--322}, publisher = {Association for Computational Linguistics}, title = {Learning beyond Datasets: Knowledge Graph Augmented Neural Networks for Natural Language Processing}, url = {https://aclanthology.org/N18-1029}, year = {2018} } @book{APA:83, address = {Washington, DC}, author = {{American Psychological Association}}, publisher = {American Psychological Association}, title = {Publications Manual}, year = {1983} } @book{arbib1987schema, author = {Arbib, Michael A and Conklin, E Jeffrey and Hill, Jane C}, publisher = {Oxford University Press}, title = {From schema theory to language.}, year = {1987} } @article{arbib1992schema, author = {Arbib, Michael A}, journal = {The Encyclopedia of Artificial Intelligence}, pages = {1427--1443}, publisher = {Wiley-Interscience}, title = {Schema theory}, volume = {2}, year = {1992} } @inproceedings{asai2020learning, author = {Akari Asai and Kazuma Hashimoto and Hannaneh Hajishirzi and Richard Socher and Caiming Xiong}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/AsaiHHSX20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering}, url = {https://openreview.net/forum?id=SJgVHkrYDH}, year = {2020} } @article{axelrod1973schema, author = {Axelrod, Robert}, journal = {American political science review}, number = {4}, pages = {1248--1266}, publisher = {Cambridge University Press}, title = {Schema theory: An information processing model of perception and cognition}, volume = {67}, year = {1973} } @inproceedings{banerjee2005meteoraa, address = {Ann Arbor, Michigan}, author = {Banerjee, Satanjeev and Lavie, Alon}, booktitle = {Proceedings of the {ACL} Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization}, pages = {65--72}, publisher = {Association for Computational Linguistics}, title = {{METEOR}: An Automatic Metric for {MT} Evaluation with Improved Correlation with Human Judgments}, url = {https://aclanthology.org/W05-0909}, year = {2005} } @inproceedings{bao2020unilmv2, author = {Hangbo Bao and Li Dong and Furu Wei and Wenhui Wang and Nan Yang and Xiaodong Liu and Yu Wang and Jianfeng Gao and Songhao Piao and Ming Zhou and Hsiao{-}Wuen Hon}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/Bao0WW0L0GP0H20.bib}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, pages = {642--652}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, title = {UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training}, url = {http://proceedings.mlr.press/v119/bao20a.html}, volume = {119}, year = {2020} } @inproceedings{bastings2017graphce, address = {Copenhagen, Denmark}, author = {Bastings, Jasmijn and Titov, Ivan and Aziz, Wilker and Marcheggiani, Diego and Sima{'}an, Khalil}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D17-1209}, pages = {1957--1967}, publisher = {Association for Computational Linguistics}, title = {Graph Convolutional Encoders for Syntax-aware Neural Machine Translation}, url = {https://aclanthology.org/D17-1209}, year = {2017} } @article{Battaglia2018RelationalIB, author = {Peter W. Battaglia and Jessica B. Hamrick and Victor Bapst and Alvaro Sanchez-Gonzalez and Vin{\'i}cius Flores Zambaldi and Mateusz Malinowski and Andrea Tacchetti and David Raposo and Adam Santoro and Ryan Faulkner and Çaglar G{\""u}lçehre and Francis Song and Andrew J. Ballard and Justin Gilmer and George E. Dahl and Ashish Vaswani and Kelsey R. Allen and Charles Nash and Victoria Langston and Chris Dyer and Nicolas Heess and Daan Wierstra and Pushmeet Kohli and Matthew Botvinick and Oriol Vinyals and Yujia Li and Razvan Pascanu}, journal = {ArXiv preprint}, title = {Relational inductive biases, deep learning, and graph networks}, url = {https://arxiv.org/abs/1806.01261}, volume = {abs/1806.01261}, year = {2018} } @article{bhakthavatsalam2020genericskb, author = {Bhakthavatsalam, Sumithra and Anastasiades, Chloe and Clark, Peter}, journal = {ArXiv preprint}, title = {GenericsKB: A Knowledge Base of Generic Statements}, url = {https://arxiv.org/abs/2005.00660}, volume = {abs/2005.00660}, year = {2020} } @inproceedings{bisk2020piqa, author = {Yonatan Bisk and Rowan Zellers and Ronan LeBras and Jianfeng Gao and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/BiskZLGC20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {7432--7439}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {{PIQA:} Reasoning about Physical Commonsense in Natural Language}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6239}, year = {2020} } @inproceedings{bollacker2008freebase, author = {Bollacker, Kurt and Evans, Colin and Paritosh, Praveen and Sturge, Tim and Taylor, Jamie}, booktitle = {SIGKDD}, organization = {AcM}, pages = {1247--1250}, title = {Freebase: a collaboratively created graph database for structuring human knowledge}, year = {2008} } @inproceedings{borsch2011, address = {Canberra, Australia}, author = {B{\""o}rschinger, Benjamin and Johnson, Mark}, booktitle = {Proceedings of the Australasian Language Technology Association Workshop 2011}, pages = {10--18}, title = {A Particle Filter algorithm for {B}ayesian Wordsegmentation}, url = {https://aclanthology.org/U11-1004}, year = {2011} } @inproceedings{c14-1001, address = {Dublin, Ireland}, author = {Harper, Mary}, booktitle = {Proceedings of {COLING} 2014, the 25th International Conference on Computational Linguistics: Technical Papers}, pages = {1}, publisher = {Dublin City University and Association for Computational Linguistics}, title = {Learning from 26 Languages: Program Management and Science in the Babel Program}, url = {https://aclanthology.org/C14-1001}, year = {2014} } @article{Chandra:81, author = {Ashok K. Chandra and Dexter C. Kozen and Larry J. Stockmeyer}, journal = {Journal of the Association for Computing Machinery}, number = {1}, pages = {114--133}, title = {Alternation}, volume = {28}, year = {1981} } @inproceedings{chen2017reading, address = {Vancouver, Canada}, author = {Chen, Danqi and Fisch, Adam and Weston, Jason and Bordes, Antoine}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1171}, pages = {1870--1879}, publisher = {Association for Computational Linguistics}, title = {Reading {W}ikipedia to Answer Open-Domain Questions}, url = {https://aclanthology.org/P17-1171}, year = {2017} } @inproceedings{Chen2019CODAHAA, address = {Minneapolis, USA}, author = {Chen, Michael and D{'}Arcy, Mike and Liu, Alisa and Fernandez, Jared and Downey, Doug}, booktitle = {Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for {NLP}}, doi = {10.18653/v1/W19-2008}, pages = {63--69}, publisher = {Association for Computational Linguistics}, title = {{CODAH}: An Adversarially-Authored Question Answering Dataset for Common Sense}, url = {https://aclanthology.org/W19-2008}, year = {2019} } @inproceedings{chi-etal-2021-infoxlm, address = {Online}, author = {Chi, Zewen and Dong, Li and Wei, Furu and Yang, Nan and Singhal, Saksham and Wang, Wenhui and Song, Xia and Mao, Xian-Ling and Huang, Heyan and Zhou, Ming}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.280}, pages = {3576--3588}, publisher = {Association for Computational Linguistics}, title = {{I}nfo{XLM}: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training}, url = {https://aclanthology.org/2021.naacl-main.280}, year = {2021} } @inproceedings{kassner-etal-2021-multilingual, address = {Online}, author = {Kassner, Nora and Dufter, Philipp and Sch{\""u}tze, Hinrich}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, pages = {3250--3258}, publisher = {Association for Computational Linguistics}, title = {Multilingual {LAMA}: Investigating Knowledge in Multilingual Pretrained Language Models}, url = {https://aclanthology.org/2021.eacl-main.284}, year = {2021} } @misc{chomsky1965aspects, author = {Chomsky, Noam}, title = {Aspects of the Theory of Syntax}, year = {1965} } @article{clark2018think, author = {Clark, Peter and Cowhey, Isaac and Etzioni, Oren and Khot, Tushar and Sabharwal, Ashish and Schoenick, Carissa and Tafjord, Oyvind}, journal = {ArXiv preprint}, title = {Think you have solved question answering? try arc, the ai2 reasoning challenge}, url = {https://arxiv.org/abs/1803.05457}, volume = {abs/1803.05457}, year = {2018} } @inproceedings{clark2020electra, author = {Kevin Clark and Minh{-}Thang Luong and Quoc V. Le and Christopher D. Manning}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ClarkLLM20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{ELECTRA:} Pre-training Text Encoders as Discriminators Rather Than Generators}, url = {https://openreview.net/forum?id=r1xMH1BtvB}, year = {2020} } @article{clark2020tydi, author = {Clark, Jonathan H. and Choi, Eunsol and Collins, Michael and Garrette, Dan and Kwiatkowski, Tom and Nikolaev, Vitaly and Palomaki, Jennimaria}, doi = {10.1162/tacl_a_00317}, journal = {Transactions of the Association for Computational Linguistics}, pages = {454--470}, title = {{T}y{D}i {QA}: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages}, url = {https://aclanthology.org/2020.tacl-1.30}, volume = {8}, year = {2020} } @article{cohen2019neural, author = {Cohen, William W and Siegler, Matthew and Hofer, Alex}, journal = {ArXiv preprint}, title = {Neural query language: A knowledge base query language for tensorflow}, url = {https://arxiv.org/abs/1905.06209}, volume = {abs/1905.06209}, year = {2019} } @inproceedings{cohen2020scalable, author = {William W. Cohen and Haitian Sun and R. Alex Hofer and Matthew Siegler}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/CohenSHS20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base}, url = {https://openreview.net/forum?id=BJlguT4YPr}, year = {2020} } @inproceedings{conneau2018xnli, address = {Brussels, Belgium}, author = {Conneau, Alexis and Rinott, Ruty and Lample, Guillaume and Williams, Adina and Bowman, Samuel and Schwenk, Holger and Stoyanov, Veselin}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1269}, pages = {2475--2485}, publisher = {Association for Computational Linguistics}, title = {{XNLI}: Evaluating Cross-lingual Sentence Representations}, url = {https://aclanthology.org/D18-1269}, year = {2018} } @inproceedings{conneau2019xlmr, address = {Online}, author = {Conneau, Alexis and Khandelwal, Kartikay and Goyal, Naman and Chaudhary, Vishrav and Wenzek, Guillaume and Guzm{\'a}n, Francisco and Grave, Edouard and Ott, Myle and Zettlemoyer, Luke and Stoyanov, Veselin}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.747}, pages = {8440--8451}, publisher = {Association for Computational Linguistics}, title = {Unsupervised Cross-lingual Representation Learning at Scale}, url = {https://aclanthology.org/2020.acl-main.747}, year = {2020} } @inproceedings{das2019multi, author = {Rajarshi Das and Shehzaad Dhuliawala and Manzil Zaheer and Andrew McCallum}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/DasDZM19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering}, url = {https://openreview.net/forum?id=HkfPSh05K7}, year = {2019} } @article{davis2015commonsense, author = {Davis, Ernest and Marcus, Gary}, journal = {Communications of the ACM}, number = {9}, pages = {92--103}, publisher = {ACM New York, NY, USA}, title = {Commonsense reasoning and commonsense knowledge in artificial intelligence}, volume = {58}, year = {2015} } @inproceedings{dblp:conf/cvpr/luybp18, author = {Jiasen Lu and Jianwei Yang and Dhruv Batra and Devi Parikh}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/LuYBP18.bib}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, doi = {10.1109/CVPR.2018.00754}, pages = {7219--7228}, publisher = {{IEEE} Computer Society}, timestamp = {Wed, 06 Feb 2019 00:00:00 +0100}, title = {Neural Baby Talk}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Lu\_Neural\_Baby\_Talk\_CVPR\_2018\_paper.html}, year = {2018} } @inproceedings{devlin2019, address = {Minneapolis, Minnesota}, author = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1423}, pages = {4171--4186}, publisher = {Association for Computational Linguistics}, title = {{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding}, url = {https://aclanthology.org/N19-1423}, year = {2019} } @inproceedings{dinu2019trainingnm, address = {Florence, Italy}, author = {Dinu, Georgiana and Mathur, Prashant and Federico, Marcello and Al-Onaizan, Yaser}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1294}, pages = {3063--3068}, publisher = {Association for Computational Linguistics}, title = {Training Neural Machine Translation to Apply Terminology Constraints}, url = {https://aclanthology.org/P19-1294}, year = {2019} } @inproceedings{dong2019unifiedlm, author = {Li Dong and Nan Yang and Wenhui Wang and Furu Wei and Xiaodong Liu and Yu Wang and Jianfeng Gao and Ming Zhou and Hsiao{-}Wuen Hon}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/00040WWLWGZH19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {13042--13054}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Unified Language Model Pre-training for Natural Language Understanding and Generation}, url = {https://proceedings.neurips.cc/paper/2019/hash/c20bb2d9a50d5ac1f713f8b34d9aac5a-Abstract.html}, year = {2019} } @inproceedings{dpr, address = {Online}, author = {Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.550}, pages = {6769--6781}, publisher = {Association for Computational Linguistics}, title = {Dense Passage Retrieval for Open-Domain Question Answering}, url = {https://aclanthology.org/2020.emnlp-main.550}, year = {2020} } @inproceedings{drkit, author = {Bhuwan Dhingra and Manzil Zaheer and Vidhisha Balachandran and Graham Neubig and Ruslan Salakhutdinov and William W. Cohen}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/DhingraZBNSC20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Differentiable Reasoning over a Virtual Knowledge Base}, url = {https://openreview.net/forum?id=SJxstlHFPH}, year = {2020} } @inproceedings{fan2018hierarchicalns, address = {Melbourne, Australia}, author = {Fan, Angela and Lewis, Mike and Dauphin, Yann}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1082}, pages = {889--898}, publisher = {Association for Computational Linguistics}, title = {Hierarchical Neural Story Generation}, url = {https://aclanthology.org/P18-1082}, year = {2018} } @inproceedings{feldman-el-yaniv-2019-multi, address = {Florence, Italy}, author = {Feldman, Yair and El-Yaniv, Ran}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1222}, pages = {2296--2309}, publisher = {Association for Computational Linguistics}, title = {Multi-Hop Paragraph Retrieval for Open-Domain Question Answering}, url = {https://aclanthology.org/P19-1222}, year = {2019} } @inproceedings{feng2018topictoessaygw, author = {Xiaocheng Feng and Ming Liu and Jiahao Liu and Bing Qin and Yibo Sun and Ting Liu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/FengLL0SL18.bib}, booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm, Sweden}, doi = {10.24963/ijcai.2018/567}, editor = {J{\'{e}}r{\^{o}}me Lang}, pages = {4078--4084}, publisher = {ijcai.org}, timestamp = {Sun, 25 Oct 2020 01:00:00 +0200}, title = {Topic-to-Essay Generation with Neural Networks}, url = {https://doi.org/10.24963/ijcai.2018/567}, year = {2018} } @inproceedings{feng2020scalable, address = {Online}, author = {Feng, Yanlin and Chen, Xinyue and Lin, Bill Yuchen and Wang, Peifeng and Yan, Jun and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.99}, pages = {1295--1309}, publisher = {Association for Computational Linguistics}, title = {Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering}, url = {https://aclanthology.org/2020.emnlp-main.99}, year = {2020} } @inproceedings{flickrentitiesijcv, author = {Bryan A. Plummer and Liwei Wang and Chris M. Cervantes and Juan C. Caicedo and Julia Hockenmaier and Svetlana Lazebnik}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/PlummerWCCHL15.bib}, booktitle = {2015 {IEEE} International Conference on Computer Vision, {ICCV} 2015, Santiago, Chile, December 7-13, 2015}, doi = {10.1109/ICCV.2015.303}, pages = {2641--2649}, publisher = {{IEEE} Computer Society}, timestamp = {Sat, 16 Sep 2017 01:00:00 +0200}, title = {Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models}, url = {https://doi.org/10.1109/ICCV.2015.303}, year = {2015} } @inproceedings{fu2018style, author = {Zhenxin Fu and Xiaoye Tan and Nanyun Peng and Dongyan Zhao and Rui Yan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/FuTPZY18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {663--670}, publisher = {{AAAI} Press}, timestamp = {Sat, 31 Aug 2019 01:00:00 +0200}, title = {Style Transfer in Text: Exploration and Evaluation}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17015}, year = {2018} } @article{garey1977rectilinear, author = {Garey, Michael R and Johnson, David S.}, journal = {SIAM Journal on Applied Mathematics}, number = {4}, pages = {826--834}, publisher = {SIAM}, title = {The rectilinear Steiner tree problem is NP-complete}, volume = {32}, year = {1977} } @inproceedings{geva-etal-2019-modeling, address = {Hong Kong, China}, author = {Geva, Mor and Goldberg, Yoav and Berant, Jonathan}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1107}, pages = {1161--1166}, publisher = {Association for Computational Linguistics}, title = {Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets}, url = {https://aclanthology.org/D19-1107}, year = {2019} } @inproceedings{gu-etal-2016-incorporating, address = {Berlin, Germany}, author = {Gu, Jiatao and Lu, Zhengdong and Li, Hang and Li, Victor O.K.}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1154}, pages = {1631--1640}, publisher = {Association for Computational Linguistics}, title = {Incorporating Copying Mechanism in Sequence-to-Sequence Learning}, url = {https://aclanthology.org/P16-1154}, year = {2016} } @inproceedings{gu2019levenshteint, author = {Jiatao Gu and Changhan Wang and Junbo Zhao}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/GuWZ19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {11179--11189}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Levenshtein Transformer}, url = {https://proceedings.neurips.cc/paper/2019/hash/675f9820626f5bc0afb47b57890b466e-Abstract.html}, year = {2019} } @inproceedings{guan2018storyeg, author = {Jian Guan and Yansen Wang and Minlie Huang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/GuanWH19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33016473}, pages = {6473--6480}, publisher = {{AAAI} Press}, timestamp = {Wed, 25 Sep 2019 01:00:00 +0200}, title = {Story Ending Generation with Incremental Encoding and Commonsense Knowledge}, url = {https://doi.org/10.1609/aaai.v33i01.33016473}, year = {2019} } @book{Gusfield:97, address = {Cambridge, UK}, author = {Dan Gusfield}, publisher = {Cambridge University Press}, title = {Algorithms on Strings, Trees and Sequences}, year = {1997} } @inproceedings{guu2020realm, author = {Kelvin Guu and Kenton Lee and Zora Tung and Panupong Pasupat and Ming{-}Wei Chang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/GuuLTPC20.bib}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, pages = {3929--3938}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, title = {Retrieval Augmented Language Model Pre-Training}, url = {http://proceedings.mlr.press/v119/guu20a.html}, volume = {119}, year = {2020} } @inproceedings{hasler2018neuralmt, address = {New Orleans, Louisiana}, author = {Hasler, Eva and de Gispert, Adri{\`a} and Iglesias, Gonzalo and Byrne, Bill}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)}, doi = {10.18653/v1/N18-2081}, pages = {506--512}, publisher = {Association for Computational Linguistics}, title = {Neural Machine Translation Decoding with Terminology Constraints}, url = {https://aclanthology.org/N18-2081}, year = {2018} } @article{Hochreiter1997LongSM, author = {Sepp Hochreiter and J{\""u}rgen Schmidhuber}, journal = {Neural Computation}, pages = {1735-1780}, title = {Long Short-Term Memory}, volume = {9}, year = {1997} } @inproceedings{hokamp2017lexicallycd, address = {Vancouver, Canada}, author = {Hokamp, Chris and Liu, Qun}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1141}, pages = {1535--1546}, publisher = {Association for Computational Linguistics}, title = {Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search}, url = {https://aclanthology.org/P17-1141}, year = {2017} } @inproceedings{hu2017towardcg, author = {Zhiting Hu and Zichao Yang and Xiaodan Liang and Ruslan Salakhutdinov and Eric P. Xing}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/HuYLSX17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {1587--1596}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Toward Controlled Generation of Text}, url = {http://proceedings.mlr.press/v70/hu17e.html}, volume = {70}, year = {2017} } @techreport{Hu2020, abstract = {Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models , a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing. To this end, we introduce the Cross-lingual TRansfer Evaluation of Multilingual Encoders (XTREME) benchmark , a multi-task benchmark for evaluating the cross-lingual generalization capabilities of multilingual representations across 40 languages and 9 tasks. We demonstrate that while models tested on English reach human performance on many tasks, there is still a sizable gap in the performance of cross-lingually transferred models, particularly on syntactic and sentence retrieval tasks. There is also a wide spread of results across languages. We release the benchmark 1 to encourage research on cross-lingual learning methods that transfer linguistic knowledge across a diverse and representative set of languages and tasks.}, author = {Hu, Junjie and Ruder, Sebastian and Siddhant, Aditya and Neubig, Graham and Firat, Orhan and Johnson, Melvin}, file = {:C\:/Users/yuchenlin/OneDrive - University of Southern California/papers/XTREME A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization - 2020 - Hu et al.pdf:pdf}, issn = {2640-3498}, mendeley-groups = {Multilingual,general NLP}, pages = {4411--4421}, publisher = {PMLR}, title = {{XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization}}, url = {https://sites.}, year = {2020} } @inproceedings{huang-etal-2019-cosmos, address = {Hong Kong, China}, author = {Huang, Lifu and Le Bras, Ronan and Bhagavatula, Chandra and Choi, Yejin}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1243}, pages = {2391--2401}, publisher = {Association for Computational Linguistics}, title = {Cosmos {QA}: Machine Reading Comprehension with Contextual Commonsense Reasoning}, url = {https://aclanthology.org/D19-1243}, year = {2019} } @inproceedings{hudson2018compositionalan, author = {Drew A. Hudson and Christopher D. Manning}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/HudsonM18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Compositional Attention Networks for Machine Reasoning}, url = {https://openreview.net/forum?id=S1Euwz-Rb}, year = {2018} } @inproceedings{hudson2019gqaan, author = {Drew A. Hudson and Christopher D. Manning}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/HudsonM19.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019}, doi = {10.1109/CVPR.2019.00686}, pages = {6700--6709}, publisher = {Computer Vision Foundation / {IEEE}}, timestamp = {Fri, 27 Mar 2020 00:00:00 +0100}, title = {{GQA:} {A} New Dataset for Real-World Visual Reasoning and Compositional Question Answering}, url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Hudson\_GQA\_A\_New\_Dataset\_for\_Real-World\_Visual\_Reasoning\_and\_Compositional\_CVPR\_2019\_paper.html}, year = {2019} } @inproceedings{j-kurisinkel-chen-2019-set, address = {Hong Kong, China}, author = {J Kurisinkel, Litton and Chen, Nancy}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1638}, pages = {6165--6175}, publisher = {Association for Computational Linguistics}, title = {Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes}, url = {https://aclanthology.org/D19-1638}, year = {2019} } @article{jaume2018image, author = {Jaume, Guillaume and Bozorgtabar, Behzad and Ekenel, Hazim Kemal and Thiran, Jean-Philippe and Gabrani, Maria}, journal = {ArXiv preprint}, title = {Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks}, url = {https://arxiv.org/abs/1811.03830}, volume = {abs/1811.03830}, year = {2018} } @article{jiang2020can, author = {Jiang, Zhengbao and Xu, Frank F. and Araki, Jun and Neubig, Graham}, doi = {10.1162/tacl_a_00324}, journal = {Transactions of the Association for Computational Linguistics}, pages = {423--438}, title = {How Can We Know What Language Models Know?}, url = {https://aclanthology.org/2020.tacl-1.28}, volume = {8}, year = {2020} } @inproceedings{jiang2020x, address = {Online}, author = {Jiang, Zhengbao and Anastasopoulos, Antonios and Araki, Jun and Ding, Haibo and Neubig, Graham}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.479}, pages = {5943--5959}, publisher = {Association for Computational Linguistics}, title = {{X}-{FACTR}: Multilingual Factual Knowledge Retrieval from Pretrained Language Models}, url = {https://aclanthology.org/2020.emnlp-main.479}, year = {2020} } @article{johnson1980mental, author = {Johnson-Laird, Philip N}, journal = {Cognitive science}, number = {1}, pages = {71--115}, publisher = {Elsevier}, title = {Mental models in cognitive science}, volume = {4}, year = {1980} } @article{johnson2019billion, author = {Johnson, Jeff and Douze, Matthijs and J{\'e}gou, Herv{\'e}}, journal = {IEEE Transactions on Big Data}, publisher = {IEEE}, title = {Billion-scale similarity search with GPUs}, year = {2019} } @inproceedings{kagnet-emnlp19, address = {Hong Kong, China}, author = {Lin, Bill Yuchen and Chen, Xinyue and Chen, Jamin and Ren, Xiang}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1282}, pages = {2829--2839}, publisher = {Association for Computational Linguistics}, title = {{K}ag{N}et: Knowledge-Aware Graph Networks for Commonsense Reasoning}, url = {https://aclanthology.org/D19-1282}, year = {2019} } @inproceedings{keysers2020measuring, author = {Daniel Keysers and Nathanael Sch{\""{a}}rli and Nathan Scales and Hylke Buisman and Daniel Furrer and Sergii Kashubin and Nikola Momchev and Danila Sinopalnikov and Lukasz Stafiniak and Tibor Tihon and Dmitry Tsarkov and Xiao Wang and Marc van Zee and Olivier Bousquet}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/KeysersSSBFKMSS20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Measuring Compositional Generalization: {A} Comprehensive Method on Realistic Data}, url = {https://openreview.net/forum?id=SygcCnNKwr}, year = {2020} } @inproceedings{khashabi2017learningwi, address = {Vancouver, Canada}, author = {Khashabi, Daniel and Khot, Tushar and Sabharwal, Ashish and Roth, Dan}, booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)}, doi = {10.18653/v1/K17-1010}, pages = {80--89}, publisher = {Association for Computational Linguistics}, title = {Learning What is Essential in Questions}, url = {https://aclanthology.org/K17-1010}, year = {2017} } @article{Khashabi2019OnTC, author = {Daniel Khashabi and Erfan Sadeqi Azer and Tushar Khot and Ashutosh Sabharwal and Dan Roth}, journal = {ArXiv preprint}, title = {On the Capabilities and Limitations of Reasoning for Natural Language Understanding}, url = {https://arxiv.org/abs/1901.02522}, volume = {abs/1901.02522}, year = {2019} } @inproceedings{khashabi2020unifiedqa, address = {Online}, author = {Khashabi, Daniel and Min, Sewon and Khot, Tushar and Sabharwal, Ashish and Tafjord, Oyvind and Clark, Peter and Hajishirzi, Hannaneh}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.171}, pages = {1896--1907}, publisher = {Association for Computational Linguistics}, title = {{UNIFIEDQA}: Crossing Format Boundaries with a Single {QA} System}, url = {https://aclanthology.org/2020.findings-emnlp.171}, year = {2020} } @inproceedings{khot2020qasc, author = {Tushar Khot and Peter Clark and Michal Guerquin and Peter Jansen and Ashish Sabharwal}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/KhotCGJS20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8082--8090}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {{QASC:} {A} Dataset for Question Answering via Sentence Composition}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6319}, year = {2020} } @inproceedings{kingma2015adamam, author = {Diederik P. Kingma and Jimmy Ba}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/journals/corr/KingmaB14.bib}, booktitle = {3rd International Conference on Learning Representations, {ICLR} 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings}, editor = {Yoshua Bengio and Yann LeCun}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Adam: {A} Method for Stochastic Optimization}, url = {http://arxiv.org/abs/1412.6980}, year = {2015} } @inproceedings{kipf2016semi, author = {Thomas N. Kipf and Max Welling}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/KipfW17.bib}, booktitle = {5th International Conference on Learning Representations, {ICLR} 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Semi-Supervised Classification with Graph Convolutional Networks}, url = {https://openreview.net/forum?id=SJU4ayYgl}, year = {2017} } @inproceedings{klein2017opennmtot, address = {Vancouver, Canada}, author = {Klein, Guillaume and Kim, Yoon and Deng, Yuntian and Senellart, Jean and Rush, Alexander}, booktitle = {Proceedings of {ACL} 2017, System Demonstrations}, pages = {67--72}, publisher = {Association for Computational Linguistics}, title = {{O}pen{NMT}: Open-Source Toolkit for Neural Machine Translation}, url = {https://aclanthology.org/P17-4012}, year = {2017} } @inproceedings{krishna2017dense, author = {Ranjay Krishna and Kenji Hata and Frederic Ren and Li Fei{-}Fei and Juan Carlos Niebles}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/KrishnaHRFN17.bib}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2017, Venice, Italy, October 22-29, 2017}, doi = {10.1109/ICCV.2017.83}, pages = {706--715}, publisher = {{IEEE} Computer Society}, timestamp = {Mon, 22 Jul 2019 01:00:00 +0200}, title = {Dense-Captioning Events in Videos}, url = {https://doi.org/10.1109/ICCV.2017.83}, year = {2017} } @article{kwiatkowski2019natural, author = {Kwiatkowski, Tom and Palomaki, Jennimaria and Redfield, Olivia and Collins, Michael and Parikh, Ankur and Alberti, Chris and Epstein, Danielle and Polosukhin, Illia and Devlin, Jacob and Lee, Kenton and Toutanova, Kristina and Jones, Llion and Kelcey, Matthew and Chang, Ming-Wei and Dai, Andrew M. and Uszkoreit, Jakob and Le, Quoc and Petrov, Slav}, doi = {10.1162/tacl_a_00276}, journal = {Transactions of the Association for Computational Linguistics}, pages = {452--466}, title = {Natural Questions: A Benchmark for Question Answering Research}, url = {https://aclanthology.org/Q19-1026}, volume = {7}, year = {2019} } @inproceedings{laixlyh17, address = {Copenhagen, Denmark}, author = {Lai, Guokun and Xie, Qizhe and Liu, Hanxiao and Yang, Yiming and Hovy, Eduard}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D17-1082}, pages = {785--794}, publisher = {Association for Computational Linguistics}, title = {{RACE}: Large-scale {R}e{A}ding Comprehension Dataset From Examinations}, url = {https://aclanthology.org/D17-1082}, year = {2017} } @inproceedings{lake2018generalization, author = {Brenden M. Lake and Marco Baroni}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/LakeB18.bib}, booktitle = {Proceedings of the 35th International Conference on Machine Learning, {ICML} 2018, Stockholmsm{\""{a}}ssan, Stockholm, Sweden, July 10-15, 2018}, editor = {Jennifer G. Dy and Andreas Krause}, pages = {2879--2888}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks}, url = {http://proceedings.mlr.press/v80/lake18a.html}, volume = {80}, year = {2018} } @inproceedings{lample2019xlm, author = {Alexis Conneau and Guillaume Lample}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ConneauL19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {7057--7067}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Cross-lingual Language Model Pretraining}, url = {https://proceedings.neurips.cc/paper/2019/hash/c04c19c2c2474dbf5f7ac4372c5b9af1-Abstract.html}, year = {2019} } @inproceedings{lan2020albert, author = {Zhenzhong Lan and Mingda Chen and Sebastian Goodman and Kevin Gimpel and Piyush Sharma and Radu Soricut}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/LanCGGSS20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language Representations}, url = {https://openreview.net/forum?id=H1eA7AEtvS}, year = {2020} } @inproceedings{lee2018deterministicnn, address = {Brussels, Belgium}, author = {Lee, Jason and Mansimov, Elman and Cho, Kyunghyun}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1149}, pages = {1173--1182}, publisher = {Association for Computational Linguistics}, title = {Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement}, url = {https://aclanthology.org/D18-1149}, year = {2018} } @inproceedings{lee2019latent, address = {Florence, Italy}, author = {Lee, Kenton and Chang, Ming-Wei and Toutanova, Kristina}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1612}, pages = {6086--6096}, publisher = {Association for Computational Linguistics}, title = {Latent Retrieval for Weakly Supervised Open Domain Question Answering}, url = {https://aclanthology.org/P19-1612}, year = {2019} } @inproceedings{Levesque2011TheWS, author = {Hector J. Levesque}, booktitle = {AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning}, title = {The Winograd Schema Challenge}, year = {2011} } @inproceedings{lewis2019bart, address = {Online}, author = {Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Veselin and Zettlemoyer, Luke}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.703}, pages = {7871--7880}, publisher = {Association for Computational Linguistics}, title = {{BART}: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, url = {https://aclanthology.org/2020.acl-main.703}, year = {2020} } @inproceedings{lewis2020retrieval, author = {Patrick S. H. Lewis and Ethan Perez and Aleksandra Piktus and Fabio Petroni and Vladimir Karpukhin and Naman Goyal and Heinrich K{\""{u}}ttler and Mike Lewis and Wen{-}tau Yih and Tim Rockt{\""{a}}schel and Sebastian Riedel and Douwe Kiela}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/LewisPPPKGKLYR020.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks}, url = {https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html}, year = {2020} } @inproceedings{li2016commonsense, address = {Berlin, Germany}, author = {Li, Xiang and Taheri, Aynaz and Tu, Lifu and Gimpel, Kevin}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1137}, pages = {1445--1455}, publisher = {Association for Computational Linguistics}, title = {Commonsense Knowledge Base Completion}, url = {https://aclanthology.org/P16-1137}, year = {2016} } @inproceedings{li2018deleterg, address = {New Orleans, Louisiana}, author = {Li, Juncen and Jia, Robin and He, He and Liang, Percy}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1169}, pages = {1865--1874}, publisher = {Association for Computational Linguistics}, title = {Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer}, url = {https://aclanthology.org/N18-1169}, year = {2018} } @inproceedings{li2020bertattackaa, address = {Online}, author = {Li, Linyang and Ma, Ruotian and Guo, Qipeng and Xue, Xiangyang and Qiu, Xipeng}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.500}, pages = {6193--6202}, publisher = {Association for Computational Linguistics}, title = {{BERT}-{ATTACK}: Adversarial Attack Against {BERT} Using {BERT}}, url = {https://aclanthology.org/2020.emnlp-main.500}, year = {2020} } @inproceedings{liang2020xglue, address = {Online}, author = {Liang, Yaobo and Duan, Nan and Gong, Yeyun and Wu, Ning and Guo, Fenfei and Qi, Weizhen and Gong, Ming and Shou, Linjun and Jiang, Daxin and Cao, Guihong and Fan, Xiaodong and Zhang, Ruofei and Agrawal, Rahul and Cui, Edward and Wei, Sining and Bharti, Taroon and Qiao, Ying and Chen, Jiun-Hung and Wu, Winnie and Liu, Shuguang and Yang, Fan and Campos, Daniel and Majumder, Rangan and Zhou, Ming}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.484}, pages = {6008--6018}, publisher = {Association for Computational Linguistics}, title = {{XGLUE}: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation}, url = {https://aclanthology.org/2020.emnlp-main.484}, year = {2020} } @inproceedings{lin2004rougeap, address = {Barcelona, Spain}, author = {Lin, Chin-Yew}, booktitle = {Text Summarization Branches Out}, pages = {74--81}, publisher = {Association for Computational Linguistics}, title = {{ROUGE}: A Package for Automatic Evaluation of Summaries}, url = {https://aclanthology.org/W04-1013}, year = {2004} } @inproceedings{Lin2014MicrosoftCC, author = {Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence}, booktitle = {European conference on computer vision}, organization = {Springer}, pages = {740--755}, title = {Microsoft coco: Common objects in context}, year = {2014} } @inproceedings{lin2018miningcd, address = {Melbourne, Australia}, author = {Lin, Bill Yuchen and Xu, Frank F. and Zhu, Kenny and Hwang, Seung-won}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1066}, pages = {709--719}, publisher = {Association for Computational Linguistics}, title = {Mining Cross-Cultural Differences and Similarities in Social Media}, url = {https://aclanthology.org/P18-1066}, year = {2018} } @inproceedings{lin2019commongen, address = {Online}, author = {Lin, Bill Yuchen and Zhou, Wangchunshu and Shen, Ming and Zhou, Pei and Bhagavatula, Chandra and Choi, Yejin and Ren, Xiang}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.165}, pages = {1823--1840}, publisher = {Association for Computational Linguistics}, title = {{C}ommon{G}en: A Constrained Text Generation Challenge for Generative Commonsense Reasoning}, url = {https://aclanthology.org/2020.findings-emnlp.165}, year = {2020} } @inproceedings{lin2020birds, address = {Online}, author = {Lin, Bill Yuchen and Lee, Seyeon and Khanna, Rahul and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.557}, pages = {6862--6868}, publisher = {Association for Computational Linguistics}, title = {{B}irds have four legs?! {N}umer{S}ense: {P}robing {N}umerical {C}ommonsense {K}nowledge of {P}re-{T}rained {L}anguage {M}odels}, url = {https://aclanthology.org/2020.emnlp-main.557}, year = {2020} } @article{Liu2019RoBERTaAR, author = {Yinhan Liu and Myle Ott and Naman Goyal and Jingfei Du and Mandar Joshi and Danqi Chen and Omer Levy and Mike Lewis and Luke Zettlemoyer and Veselin Stoyanov}, journal = {ArXiv preprint}, title = {RoBERTa: A Robustly Optimized BERT Pretraining Approach}, url = {https://arxiv.org/abs/1907.11692}, volume = {abs/1907.11692}, year = {2019} } @article{lsmdc, author = {Rohrbach, Anna and Torabi, Atousa and Rohrbach, Marcus and Tandon, Niket and Pal, Christopher and Larochelle, Hugo and Courville, Aaron and Schiele, Bernt}, journal = {International Journal of Computer Vision}, number = {1}, pages = {94--120}, publisher = {Springer}, title = {Movie description}, volume = {123}, year = {2017} } @inproceedings{luo2019adr, author = {Fuli Luo and Peng Li and Jie Zhou and Pengcheng Yang and Baobao Chang and Xu Sun and Zhifang Sui}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/LuoLZYCSS19.bib}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, doi = {10.24963/ijcai.2019/711}, editor = {Sarit Kraus}, pages = {5116--5122}, publisher = {ijcai.org}, timestamp = {Wed, 22 Jan 2020 00:00:00 +0100}, title = {A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer}, url = {https://doi.org/10.24963/ijcai.2019/711}, year = {2019} } @inproceedings{luo2019towardsft, address = {Florence, Italy}, author = {Luo, Fuli and Li, Peng and Yang, Pengcheng and Zhou, Jie and Tan, Yutong and Chang, Baobao and Sui, Zhifang and Sun, Xu}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1194}, pages = {2013--2022}, publisher = {Association for Computational Linguistics}, title = {Towards Fine-grained Text Sentiment Transfer}, url = {https://aclanthology.org/P19-1194}, year = {2019} } @inproceedings{luong2015effectiveat, address = {Lisbon, Portugal}, author = {Luong, Thang and Pham, Hieu and Manning, Christopher D.}, booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D15-1166}, pages = {1412--1421}, publisher = {Association for Computational Linguistics}, title = {Effective Approaches to Attention-based Neural Machine Translation}, url = {https://aclanthology.org/D15-1166}, year = {2015} } @inproceedings{lv2020graph, author = {Shangwen Lv and Daya Guo and Jingjing Xu and Duyu Tang and Nan Duan and Ming Gong and Linjun Shou and Daxin Jiang and Guihong Cao and Songlin Hu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/LvGXTDGSJCH20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8449--8456}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6364}, year = {2020} } @inproceedings{marcheggiani2017encodingsw, address = {Copenhagen, Denmark}, author = {Marcheggiani, Diego and Titov, Ivan}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D17-1159}, pages = {1506--1515}, publisher = {Association for Computational Linguistics}, title = {Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling}, url = {https://aclanthology.org/D17-1159}, year = {2017} } @inproceedings{mariannmt, address = {Melbourne, Australia}, author = {Junczys-Dowmunt, Marcin and Grundkiewicz, Roman and Dwojak, Tomasz and Hoang, Hieu and Heafield, Kenneth and Neckermann, Tom and Seide, Frank and Germann, Ulrich and Aji, Alham Fikri and Bogoychev, Nikolay and Martins, Andr{\'e} F. T. and Birch, Alexandra}, booktitle = {Proceedings of {ACL} 2018, System Demonstrations}, doi = {10.18653/v1/P18-4020}, pages = {116--121}, publisher = {Association for Computational Linguistics}, title = {{M}arian: Fast Neural Machine Translation in {C}++}, url = {https://aclanthology.org/P18-4020}, year = {2018} } @article{mbart, author = {Liu, Yinhan and Gu, Jiatao and Goyal, Naman and Li, Xian and Edunov, Sergey and Ghazvininejad, Marjan and Lewis, Mike and Zettlemoyer, Luke}, doi = {10.1162/tacl_a_00343}, journal = {Transactions of the Association for Computational Linguistics}, pages = {726--742}, title = {Multilingual Denoising Pre-training for Neural Machine Translation}, url = {https://aclanthology.org/2020.tacl-1.47}, volume = {8}, year = {2020} } @inproceedings{miao2018cgmhcs, author = {Ning Miao and Hao Zhou and Lili Mou and Rui Yan and Lei Li}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/MiaoZMYL19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33016834}, pages = {6834--6842}, publisher = {{AAAI} Press}, timestamp = {Wed, 09 Sep 2020 01:00:00 +0200}, title = {{CGMH:} Constrained Sentence Generation by Metropolis-Hastings Sampling}, url = {https://doi.org/10.1609/aaai.v33i01.33016834}, year = {2019} } @inproceedings{mihaylov2018canas, address = {Brussels, Belgium}, author = {Mihaylov, Todor and Clark, Peter and Khot, Tushar and Sabharwal, Ashish}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1260}, pages = {2381--2391}, publisher = {Association for Computational Linguistics}, title = {Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering}, url = {https://aclanthology.org/D18-1260}, year = {2018} } @inproceedings{mihaylov2018knowledgeablere, address = {Melbourne, Australia}, author = {Mihaylov, Todor and Frank, Anette}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1076}, pages = {821--832}, publisher = {Association for Computational Linguistics}, title = {Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge}, url = {https://aclanthology.org/P18-1076}, year = {2018} } @book{moore2013development, author = {Moore, Chris}, publisher = {Psychology Press}, title = {The development of commonsense psychology}, year = {2013} } @inproceedings{mt5, address = {Online}, author = {Xue, Linting and Constant, Noah and Roberts, Adam and Kale, Mihir and Al-Rfou, Rami and Siddhant, Aditya and Barua, Aditya and Raffel, Colin}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.41}, pages = {483--498}, publisher = {Association for Computational Linguistics}, title = {m{T}5: A Massively Multilingual Pre-trained Text-to-Text Transformer}, url = {https://aclanthology.org/2021.naacl-main.41}, year = {2021} } @inproceedings{P16-1001, address = {Berlin, Germany}, author = {Goodman, James and Vlachos, Andreas and Naradowsky, Jason}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P16-1001}, pages = {1--11}, publisher = {Association for Computational Linguistics}, title = {Noise reduction and targeted exploration in imitation learning for {A}bstract {M}eaning {R}epresentation parsing}, url = {https://aclanthology.org/P16-1001}, year = {2016} } @inproceedings{papineni2001bleuam, address = {Philadelphia, Pennsylvania, USA}, author = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing}, booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics}, doi = {10.3115/1073083.1073135}, pages = {311--318}, publisher = {Association for Computational Linguistics}, title = {{B}leu: a Method for Automatic Evaluation of Machine Translation}, url = {https://aclanthology.org/P02-1040}, year = {2002} } @inproceedings{Papineni2002BleuAM, address = {Philadelphia, Pennsylvania, USA}, author = {Papineni, Kishore and Roukos, Salim and Ward, Todd and Zhu, Wei-Jing}, booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics}, doi = {10.3115/1073083.1073135}, pages = {311--318}, publisher = {Association for Computational Linguistics}, title = {{B}leu: a Method for Automatic Evaluation of Machine Translation}, url = {https://aclanthology.org/P02-1040}, year = {2002} } @inproceedings{pascanu2014howtc, author = {Razvan Pascanu and {\c{C}}aglar G{\""{u}}l{\c{c}}ehre and Kyunghyun Cho and Yoshua Bengio}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/journals/corr/PascanuGCB13.bib}, booktitle = {2nd International Conference on Learning Representations, {ICLR} 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings}, editor = {Yoshua Bengio and Yann LeCun}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {How to Construct Deep Recurrent Neural Networks}, url = {http://arxiv.org/abs/1312.6026}, year = {2014} } @inproceedings{petroni2019language, address = {Hong Kong, China}, author = {Petroni, Fabio and Rockt{\""a}schel, Tim and Riedel, Sebastian and Lewis, Patrick and Bakhtin, Anton and Wu, Yuxiang and Miller, Alexander}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1250}, pages = {2463--2473}, publisher = {Association for Computational Linguistics}, title = {Language Models as Knowledge Bases?}, url = {https://aclanthology.org/D19-1250}, year = {2019} } @inproceedings{ponti2020xcopa, address = {Online}, author = {Ponti, Edoardo Maria and Glava{\v{s}}, Goran and Majewska, Olga and Liu, Qianchu and Vuli{\'c}, Ivan and Korhonen, Anna}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.185}, pages = {2362--2376}, publisher = {Association for Computational Linguistics}, title = {{XCOPA}: A Multilingual Dataset for Causal Commonsense Reasoning}, url = {https://aclanthology.org/2020.emnlp-main.185}, year = {2020} } @inproceedings{post-vilar-2018-fast, address = {New Orleans, Louisiana}, author = {Post, Matt and Vilar, David}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1119}, pages = {1314--1324}, publisher = {Association for Computational Linguistics}, title = {Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation}, url = {https://aclanthology.org/N18-1119}, year = {2018} } @inproceedings{puduppully-etal-2017-transition, address = {Valencia, Spain}, author = {Puduppully, Ratish and Zhang, Yue and Shrivastava, Manish}, booktitle = {Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers}, pages = {643--654}, publisher = {Association for Computational Linguistics}, title = {Transition-Based Deep Input Linearization}, url = {https://aclanthology.org/E17-1061}, year = {2017} } @inproceedings{qi2019answering, address = {Hong Kong, China}, author = {Qi, Peng and Lin, Xiaowen and Mehr, Leo and Wang, Zijian and Manning, Christopher D.}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1261}, pages = {2590--2602}, publisher = {Association for Computational Linguistics}, title = {Answering Complex Open-domain Questions Through Iterative Query Generation}, url = {https://aclanthology.org/D19-1261}, year = {2019} } @inproceedings{qi2020stanza, address = {Online}, author = {Qi, Peng and Zhang, Yuhao and Zhang, Yuhui and Bolton, Jason and Manning, Christopher D.}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations}, doi = {10.18653/v1/2020.acl-demos.14}, pages = {101--108}, publisher = {Association for Computational Linguistics}, title = {{S}tanza: A Python Natural Language Processing Toolkit for Many Human Languages}, url = {https://aclanthology.org/2020.acl-demos.14}, year = {2020} } @inproceedings{qiao2019mirrorganlt, author = {Tingting Qiao and Jing Zhang and Duanqing Xu and Dacheng Tao}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/QiaoZXT19.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019}, doi = {10.1109/CVPR.2019.00160}, pages = {1505--1514}, publisher = {Computer Vision Foundation / {IEEE}}, timestamp = {Wed, 05 Feb 2020 00:00:00 +0100}, title = {MirrorGAN: Learning Text-To-Image Generation by Redescription}, url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Qiao\_MirrorGAN\_Learning\_Text-To-Image\_Generation\_by\_Redescription\_CVPR\_2019\_paper.html}, year = {2019} } @article{radford2018improving, author = {Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya}, title = {Improving language understanding by generative pre-training}, year = {2018} } @misc{radford2019language, author = {Radford, Alec and Wu, Jeff and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya}, title = {Language Models are Unsupervised Multitask Learners}, year = {2019} } @article{raffel2019exploring, author = {Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J}, journal = {ArXiv preprint}, title = {Exploring the limits of transfer learning with a unified text-to-text transformer}, url = {https://arxiv.org/abs/1910.10683}, volume = {abs/1910.10683}, year = {2019} } @inproceedings{rajani2019explainyl, address = {Florence, Italy}, author = {Rajani, Nazneen Fatema and McCann, Bryan and Xiong, Caiming and Socher, Richard}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1487}, pages = {4932--4942}, publisher = {Association for Computational Linguistics}, title = {Explain Yourself! Leveraging Language Models for Commonsense Reasoning}, url = {https://aclanthology.org/P19-1487}, year = {2019} } @inproceedings{rajpurkar2016squad10, address = {Austin, Texas}, author = {Rajpurkar, Pranav and Zhang, Jian and Lopyrev, Konstantin and Liang, Percy}, booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D16-1264}, pages = {2383--2392}, publisher = {Association for Computational Linguistics}, title = {{SQ}u{AD}: 100,000+ Questions for Machine Comprehension of Text}, url = {https://aclanthology.org/D16-1264}, year = {2016} } @article{Schick2023ToolformerLM, author = {Timo Schick and Jane Dwivedi-Yu and Roberto Dess{\`i} and Roberta Raileanu and Maria Lomeli and Luke Zettlemoyer and Nicola Cancedda and Thomas Scialom}, journal = {ArXiv preprint}, title = {Toolformer: Language Models Can Teach Themselves to Use Tools}, url = {https://arxiv.org/abs/2302.04761}, volume = {abs/2302.04761}, year = {2023} } @article{interactiveNLP, author = {Zekun Wang and Ge Zhang and Kexin Yang and Ning Shi and Wangchunshu Zhou and Shaochun Hao and Guangzheng Xiong and Yizhi Li and Mong Yuan Sim and Xiuying Chen and Qingqing Zhu and Zhenzhu Yang and Adam Nik and Qi Liu and Chenghua Lin and Shi Wang and Ruibo Liu and Wenhu Chen and Ke Xu and Dayiheng Liu and Yike Guo and Jie Fu}, journal = {ArXiv}, title = {Interactive Natural Language Processing}, year = {2023} } @article{Lu2023ChameleonPC, author = {Pan Lu and Baolin Peng and Hao Cheng and Michel Galley and Kai-Wei Chang and Ying Nian Wu and Song-Chun Zhu and Jianfeng Gao}, journal = {ArXiv preprint}, title = {Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models}, url = {https://arxiv.org/abs/2304.09842}, volume = {abs/2304.09842}, year = {2023} } @article{openagi, author = {Ge, Yingqiang and Hua, Wenyue and Ji, Jianchao and Tan, Juntao and Xu, Shuyuan and Zhang, Yongfeng}, journal = {arXiv}, title = {OpenAGI: When LLM Meets Domain Experts}, year = {2023} } @article{Shen2023HuggingGPTSA, author = {Yongliang Shen and Kaitao Song and Xu Tan and Dong Sheng Li and Weiming Lu and Yue Ting Zhuang}, journal = {ArXiv preprint}, title = {HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace}, url = {https://arxiv.org/abs/2303.17580}, volume = {abs/2303.17580}, year = {2023} } @inproceedings{reimers2019sentencebertse, address = {Hong Kong, China}, author = {Reimers, Nils and Gurevych, Iryna}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1410}, pages = {3982--3992}, publisher = {Association for Computational Linguistics}, title = {Sentence-{BERT}: Sentence Embeddings using {S}iamese {BERT}-Networks}, url = {https://aclanthology.org/D19-1410}, year = {2019} } @inproceedings{roberts2020much, address = {Online}, author = {Roberts, Adam and Raffel, Colin and Shazeer, Noam}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.437}, pages = {5418--5426}, publisher = {Association for Computational Linguistics}, title = {How Much Knowledge Can You Pack Into the Parameters of a Language Model?}, url = {https://aclanthology.org/2020.emnlp-main.437}, year = {2020} } @inproceedings{Sakaguchi2019WINOGRANDEAA, author = {Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/SakaguchiBBC20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8732--8740}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {WinoGrande: An Adversarial Winograd Schema Challenge at Scale}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6399}, year = {2020} } @inproceedings{salazar2020maskedlm, address = {Online}, author = {Salazar, Julian and Liang, Davis and Nguyen, Toan Q. and Kirchhoff, Katrin}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.240}, pages = {2699--2712}, publisher = {Association for Computational Linguistics}, title = {Masked Language Model Scoring}, url = {https://aclanthology.org/2020.acl-main.240}, year = {2020} } @article{salton1988term, author = {Salton, Gerard and Buckley, Christopher}, journal = {Information processing \& management}, number = {5}, pages = {513--523}, publisher = {Elsevier}, title = {Term-weighting approaches in automatic text retrieval}, volume = {24}, year = {1988} } @article{Sanh2019DistilBERTAD, author = {Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf}, journal = {ArXiv preprint}, title = {DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter}, url = {https://arxiv.org/abs/1910.01108}, volume = {abs/1910.01108}, year = {2019} } @inproceedings{santoro2017asn, author = {Adam Santoro and David Raposo and David G. T. Barrett and Mateusz Malinowski and Razvan Pascanu and Peter W. Battaglia and Tim Lillicrap}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SantoroRBMPBL17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {4967--4976}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {A simple neural network module for relational reasoning}, url = {https://proceedings.neurips.cc/paper/2017/hash/e6acf4b0f69f6f6e60e9a815938aa1ff-Abstract.html}, year = {2017} } @inproceedings{sap-etal-2019-social, address = {Hong Kong, China}, author = {Sap, Maarten and Rashkin, Hannah and Chen, Derek and Le Bras, Ronan and Choi, Yejin}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1454}, pages = {4463--4473}, publisher = {Association for Computational Linguistics}, title = {Social {IQ}a: Commonsense Reasoning about Social Interactions}, url = {https://aclanthology.org/D19-1454}, year = {2019} } @inproceedings{sap2018atomic, author = {Maarten Sap and Ronan Le Bras and Emily Allaway and Chandra Bhagavatula and Nicholas Lourie and Hannah Rashkin and Brendan Roof and Noah A. Smith and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/SapBABLRRSC19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33013027}, pages = {3027--3035}, publisher = {{AAAI} Press}, timestamp = {Thu, 13 Aug 2020 01:00:00 +0200}, title = {{ATOMIC:} An Atlas of Machine Commonsense for If-Then Reasoning}, url = {https://doi.org/10.1609/aaai.v33i01.33013027}, year = {2019} } @inproceedings{scann, author = {Ruiqi Guo and Philip Sun and Erik Lindgren and Quan Geng and David Simcha and Felix Chern and Sanjiv Kumar}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/GuoSLGSCK20.bib}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, pages = {3887--3896}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, title = {Accelerating Large-Scale Inference with Anisotropic Vector Quantization}, url = {http://proceedings.mlr.press/v119/guo20h.html}, volume = {119}, year = {2020} } @inproceedings{Schlichtkrull2018ModelingRD, author = {Michael Sejr Schlichtkrull and Thomas N. Kipf and Peter Bloem and Rianne van den Berg and Ivan Titov and Max Welling}, booktitle = {European Semantic Web Conference}, title = {Modeling Relational Data with Graph Convolutional Networks}, year = {2018} } @inproceedings{see2017gettt, address = {Vancouver, Canada}, author = {See, Abigail and Liu, Peter J. and Manning, Christopher D.}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1099}, pages = {1073--1083}, publisher = {Association for Computational Linguistics}, title = {Get To The Point: Summarization with Pointer-Generator Networks}, url = {https://aclanthology.org/P17-1099}, year = {2017} } @inproceedings{seo2019real, address = {Florence, Italy}, author = {Seo, Minjoon and Lee, Jinhyuk and Kwiatkowski, Tom and Parikh, Ankur and Farhadi, Ali and Hajishirzi, Hannaneh}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1436}, pages = {4430--4441}, publisher = {Association for Computational Linguistics}, title = {Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index}, url = {https://aclanthology.org/P19-1436}, year = {2019} } @inproceedings{sharma2018conceptualca, address = {Melbourne, Australia}, author = {Sharma, Piyush and Ding, Nan and Goodman, Sebastian and Soricut, Radu}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1238}, pages = {2556--2565}, publisher = {Association for Computational Linguistics}, title = {Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning}, url = {https://aclanthology.org/P18-1238}, year = {2018} } @article{shen2014entity, author = {Shen, Wei and Wang, Jianyong and Han, Jiawei}, journal = {TKDE}, number = {2}, pages = {443--460}, publisher = {IEEE}, title = {Entity linking with a knowledge base: Issues, techniques, and solutions}, volume = {27}, year = {2014} } @inproceedings{Singh2002OpenMC, author = {Singh, Push and Lin, Thomas and Mueller, Erik T and Lim, Grace and Perkins, Travell and Zhu, Wan Li}, booktitle = {OTM Confederated International Conferences"" On the Move to Meaningful Internet Systems""}, organization = {Springer}, pages = {1223--1237}, title = {Open Mind Common Sense: Knowledge acquisition from the general public}, year = {2002} } @inproceedings{singh2018semanticallyea, address = {Melbourne, Australia}, author = {Ribeiro, Marco Tulio and Singh, Sameer and Guestrin, Carlos}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P18-1079}, pages = {856--865}, publisher = {Association for Computational Linguistics}, title = {Semantically Equivalent Adversarial Rules for Debugging {NLP} models}, url = {https://aclanthology.org/P18-1079}, year = {2018} } @inproceedings{snli:emnlp2015, address = {Lisbon, Portugal}, author = {Bowman, Samuel R. and Angeli, Gabor and Potts, Christopher and Manning, Christopher D.}, booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D15-1075}, pages = {632--642}, publisher = {Association for Computational Linguistics}, title = {A large annotated corpus for learning natural language inference}, url = {https://aclanthology.org/D15-1075}, year = {2015} } @inproceedings{speer2017conceptnet5a, author = {Robyn Speer and Joshua Chin and Catherine Havasi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/SpeerCH17.bib}, booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, {USA}}, editor = {Satinder P. Singh and Shaul Markovitch}, pages = {4444--4451}, publisher = {{AAAI} Press}, timestamp = {Fri, 31 May 2019 01:00:00 +0200}, title = {ConceptNet 5.5: An Open Multilingual Graph of General Knowledge}, url = {http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14972}, year = {2017} } @inproceedings{stern2019insertiontf, author = {Mitchell Stern and William Chan and Jamie Kiros and Jakob Uszkoreit}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/SternCKU19.bib}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, pages = {5976--5985}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 11 Jun 2019 01:00:00 +0200}, title = {Insertion Transformer: Flexible Sequence Generation via Insertion Operations}, url = {http://proceedings.mlr.press/v97/stern19a.html}, volume = {97}, year = {2019} } @inproceedings{sun2018open, address = {Brussels, Belgium}, author = {Sun, Haitian and Dhingra, Bhuwan and Zaheer, Manzil and Mazaitis, Kathryn and Salakhutdinov, Ruslan and Cohen, William}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1455}, pages = {4231--4242}, publisher = {Association for Computational Linguistics}, title = {Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text}, url = {https://aclanthology.org/D18-1455}, year = {2018} } @inproceedings{sun2019pullnet, address = {Hong Kong, China}, author = {Sun, Haitian and Bedrax-Weiss, Tania and Cohen, William}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1242}, pages = {2380--2390}, publisher = {Association for Computational Linguistics}, title = {{P}ull{N}et: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text}, url = {https://aclanthology.org/D19-1242}, year = {2019} } @inproceedings{susanto2020lexically, address = {Online}, author = {Susanto, Raymond Hendy and Chollampatt, Shamil and Tan, Liling}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.325}, pages = {3536--3543}, publisher = {Association for Computational Linguistics}, title = {Lexically Constrained Neural Machine Translation with {L}evenshtein Transformer}, url = {https://aclanthology.org/2020.acl-main.325}, year = {2020} } @inproceedings{sutskever2014sequencets, author = {Ilya Sutskever and Oriol Vinyals and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SutskeverVL14.bib}, booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada}, editor = {Zoubin Ghahramani and Max Welling and Corinna Cortes and Neil D. Lawrence and Kilian Q. Weinberger}, pages = {3104--3112}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Sequence to Sequence Learning with Neural Networks}, url = {https://proceedings.neurips.cc/paper/2014/hash/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html}, year = {2014} } @article{t5, author = {Raffel, Colin and Shazeer, Noam and Roberts, Adam and Lee, Katherine and Narang, Sharan and Matena, Michael and Zhou, Yanqi and Li, Wei and Liu, Peter J}, journal = {Journal of Machine Learning Research}, number = {140}, pages = {1--67}, title = {Exploring the limits of transfer learning with a unified text-to-text transformer}, volume = {21}, year = {2020} } @inproceedings{Talmor2018commonsenseqaaq, address = {Minneapolis, Minnesota}, author = {Talmor, Alon and Herzig, Jonathan and Lourie, Nicholas and Berant, Jonathan}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1421}, pages = {4149--4158}, publisher = {Association for Computational Linguistics}, title = {{C}ommonsense{QA}: A Question Answering Challenge Targeting Commonsense Knowledge}, url = {https://aclanthology.org/N19-1421}, year = {2019} } @inproceedings{tandon2017webchild2, address = {Vancouver, Canada}, author = {Tandon, Niket and de Melo, Gerard and Weikum, Gerhard}, booktitle = {Proceedings of {ACL} 2017, System Demonstrations}, pages = {115--120}, publisher = {Association for Computational Linguistics}, title = {{W}eb{C}hild 2.0 : Fine-Grained Commonsense Knowledge Distillation}, url = {https://aclanthology.org/P17-4020}, year = {2017} } @inproceedings{tiedemann2016opus, address = {Riga, Latvia}, author = {Tiedemann, J{\""o}rg}, booktitle = {Proceedings of the 19th Annual Conference of the European Association for Machine Translation: Projects/Products}, publisher = {Baltic Journal of Modern Computing}, title = {{OPUS} {--} parallel corpora for everyone}, url = {https://aclanthology.org/2016.eamt-2.8}, year = {2016} } @article{Trinh2018ASM, author = {Trieu H. Trinh and Quoc V. Le}, journal = {ArXiv preprint}, title = {A Simple Method for Commonsense Reasoning}, url = {https://arxiv.org/abs/1806.02847}, volume = {abs/1806.02847}, year = {2018} } @article{trinh2019do, author = {Trieu H. Trinh and Quoc V. Le}, journal = {OpenReview}, title = {Do Language Models Have Common Sense?}, volume = {ICLR submissions}, year = {2019} } @inproceedings{vaswani2017attentionia, author = {Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/VaswaniSPUJGKP17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {5998--6008}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Attention is All you Need}, url = {https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html}, year = {2017} } @inproceedings{vedantam2014ciderci, author = {Ramakrishna Vedantam and C. Lawrence Zitnick and Devi Parikh}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/VedantamZP15.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2015, Boston, MA, USA, June 7-12, 2015}, doi = {10.1109/CVPR.2015.7299087}, pages = {4566--4575}, publisher = {{IEEE} Computer Society}, timestamp = {Thu, 25 May 2017 01:00:00 +0200}, title = {CIDEr: Consensus-based image description evaluation}, url = {https://doi.org/10.1109/CVPR.2015.7299087}, year = {2015} } @inproceedings{wang-etal-2019-make, address = {Florence, Italy}, author = {Wang, Cunxiang and Liang, Shuailong and Zhang, Yue and Li, Xiaonan and Gao, Tian}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1393}, pages = {4020--4026}, publisher = {Association for Computational Linguistics}, title = {Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation}, url = {https://aclanthology.org/P19-1393}, year = {2019} } @inproceedings{wang-etal-2020-semeval, address = {Barcelona (online)}, author = {Wang, Cunxiang and Liang, Shuailong and Jin, Yili and Wang, Yilong and Zhu, Xiaodan and Zhang, Yue}, booktitle = {Proceedings of the Fourteenth Workshop on Semantic Evaluation}, pages = {307--321}, publisher = {International Committee for Computational Linguistics}, title = {{S}em{E}val-2020 Task 4: Commonsense Validation and Explanation}, url = {https://aclanthology.org/2020.semeval-1.39}, year = {2020} } @inproceedings{wang2014knowledgege, author = {Zhen Wang and Jianwen Zhang and Jianlin Feng and Zheng Chen}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/WangZFC14.bib}, booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence, July 27 -31, 2014, Qu{\'{e}}bec City, Qu{\'{e}}bec, Canada}, editor = {Carla E. Brodley and Peter Stone}, pages = {1112--1119}, publisher = {{AAAI} Press}, timestamp = {Mon, 18 Dec 2017 00:00:00 +0100}, title = {Knowledge Graph Embedding by Translating on Hyperplanes}, url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/view/8531}, year = {2014} } @inproceedings{wang2018glue, author = {Alex Wang and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/WangSMHLB19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {{GLUE:} {A} Multi-Task Benchmark and Analysis Platform for Natural Language Understanding}, url = {https://openreview.net/forum?id=rJ4km2R5t7}, year = {2019} } @inproceedings{Wang2018ImprovingNL, author = {Xiaoyan Wang and Pavan Kapanipathi and Ryan Musa and Mo Yu and Kartik Talamadupula and Ibrahim Abdelaziz and Maria Chang and Achille Fokoue and Bassem Makni and Nicholas Mattei and Michael Witbrock}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/WangKMYTACFMMW19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33017208}, pages = {7208--7215}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {Improving Natural Language Inference Using External Knowledge in the Science Questions Domain}, url = {https://doi.org/10.1609/aaai.v33i01.33017208}, year = {2019} } @inproceedings{Wang2019ImprovingNL, author = {Xiaoyan Wang and Pavan Kapanipathi and Ryan Musa and Mo Yu and Kartik Talamadupula and Ibrahim Abdelaziz and Maria Chang and Achille Fokoue and Bassem Makni and Nicholas Mattei and Michael Witbrock}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/WangKMYTACFMMW19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33017208}, pages = {7208--7215}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {Improving Natural Language Inference Using External Knowledge in the Science Questions Domain}, url = {https://doi.org/10.1609/aaai.v33i01.33017208}, year = {2019} } @inproceedings{wang2019superglue, author = {Alex Wang and Yada Pruksachatkun and Nikita Nangia and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/WangPNSMHLB19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {3261--3275}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {SuperGLUE: {A} Stickier Benchmark for General-Purpose Language Understanding Systems}, url = {https://proceedings.neurips.cc/paper/2019/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html}, year = {2019} } @inproceedings{wang_2019_iccv, author = {Xin Wang and Jiawei Wu and Junkun Chen and Lei Li and Yuan{-}Fang Wang and William Yang Wang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/WangWCLWW19.bib}, booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2019, Seoul, Korea (South), October 27 - November 2, 2019}, doi = {10.1109/ICCV.2019.00468}, pages = {4580--4590}, publisher = {{IEEE}}, timestamp = {Wed, 09 Sep 2020 01:00:00 +0200}, title = {VaTeX: {A} Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research}, url = {https://doi.org/10.1109/ICCV.2019.00468}, year = {2019} } @article{weissenborn2017dynamic, author = {Weissenborn, Dirk and Ko{\v{c}}isk{\`y}, Tom{\'a}{\v{s}} and Dyer, Chris}, journal = {ArXiv preprint}, title = {Dynamic integration of background knowledge in neural NLU systems}, url = {https://arxiv.org/abs/1706.02596}, volume = {abs/1706.02596}, year = {2017} } @inproceedings{Weissenborn2018DynamicIO, author = {Dirk Weissenborn and Tom'avs Kovcisk'y and Chris Dyer}, title = {Dynamic Integration of Background Knowledge in Neural NLU Systems}, year = {2018} } @article{Wolf2019HuggingFacesTS, author = {Thomas Wolf and Lysandre Debut and Victor Sanh and Julien Chaumond and Clement Delangue and Anthony Moi and Pierric Cistac and Tim Rault and R'emi Louf and Morgan Funtowicz and Jamie Brew}, journal = {ArXiv preprint}, title = {HuggingFace's Transformers: State-of-the-art Natural Language Processing}, url = {https://arxiv.org/abs/1910.03771}, volume = {abs/1910.03771}, year = {2019} } @inproceedings{xu2018automaticeo, address = {Melbourne, Australia}, author = {Xu, Frank F. and Lin, Bill Yuchen and Zhu, Kenny}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, doi = {10.18653/v1/P18-2016}, pages = {96--101}, publisher = {Association for Computational Linguistics}, title = {Automatic Extraction of Commonsense {L}ocated{N}ear Knowledge}, url = {https://aclanthology.org/P18-2016}, year = {2018} } @inproceedings{yang2016hierarchicalan, address = {San Diego, California}, author = {Yang, Zichao and Yang, Diyi and Dyer, Chris and He, Xiaodong and Smola, Alex and Hovy, Eduard}, booktitle = {Proceedings of the 2016 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/N16-1174}, pages = {1480--1489}, publisher = {Association for Computational Linguistics}, title = {Hierarchical Attention Networks for Document Classification}, url = {https://aclanthology.org/N16-1174}, year = {2016} } @inproceedings{yang2017leveragingkb, address = {Vancouver, Canada}, author = {Yang, Bishan and Mitchell, Tom}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1132}, pages = {1436--1446}, publisher = {Association for Computational Linguistics}, title = {Leveraging Knowledge Bases in {LSTM}s for Improving Machine Reading}, url = {https://aclanthology.org/P17-1132}, year = {2017} } @inproceedings{yang2018hotpotqa, address = {Brussels, Belgium}, author = {Yang, Zhilin and Qi, Peng and Zhang, Saizheng and Bengio, Yoshua and Cohen, William and Salakhutdinov, Ruslan and Manning, Christopher D.}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1259}, pages = {2369--2380}, publisher = {Association for Computational Linguistics}, title = {{H}otpot{QA}: A Dataset for Diverse, Explainable Multi-hop Question Answering}, url = {https://aclanthology.org/D18-1259}, year = {2018} } @inproceedings{yang2019enhancingtg, address = {Florence, Italy}, author = {Yang, Pengcheng and Li, Lei and Luo, Fuli and Liu, Tianyu and Sun, Xu}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1193}, pages = {2002--2012}, publisher = {Association for Computational Linguistics}, title = {Enhancing Topic-to-Essay Generation with External Commonsense Knowledge}, url = {https://aclanthology.org/P19-1193}, year = {2019} } @inproceedings{yang2019knowledgeablesa, author = {Pengcheng Yang and Fuli Luo and Peng Chen and Lei Li and Zhiyi Yin and Xiaodong He and Xu Sun}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/YangLCLYHS19.bib}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, doi = {10.24963/ijcai.2019/744}, editor = {Sarit Kraus}, pages = {5356--5362}, publisher = {ijcai.org}, timestamp = {Wed, 02 Sep 2020 01:00:00 +0200}, title = {Knowledgeable Storyteller: {A} Commonsense-Driven Generative Model for Visual Storytelling}, url = {https://doi.org/10.24963/ijcai.2019/744}, year = {2019} } @inproceedings{yang2019xlnetga, author = {Zhilin Yang and Zihang Dai and Yiming Yang and Jaime G. Carbonell and Ruslan Salakhutdinov and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/YangDYCSL19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {5754--5764}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding}, url = {https://proceedings.neurips.cc/paper/2019/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html}, year = {2019} } @inproceedings{yao2019plan, author = {Lili Yao and Nanyun Peng and Ralph M. Weischedel and Kevin Knight and Dongyan Zhao and Rui Yan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/YaoPWK0Y19.bib}, booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019}, doi = {10.1609/aaai.v33i01.33017378}, pages = {7378--7385}, publisher = {{AAAI} Press}, timestamp = {Tue, 02 Feb 2021 00:00:00 +0100}, title = {Plan-and-Write: Towards Better Automatic Storytelling}, url = {https://doi.org/10.1609/aaai.v33i01.33017378}, year = {2019} } @article{young-etal-2014-image, author = {Young, Peter and Lai, Alice and Hodosh, Micah and Hockenmaier, Julia}, doi = {10.1162/tacl_a_00166}, journal = {Transactions of the Association for Computational Linguistics}, pages = {67--78}, title = {From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions}, url = {https://aclanthology.org/Q14-1006}, volume = {2}, year = {2014} } @inproceedings{zellers2018swagal, address = {Brussels, Belgium}, author = {Zellers, Rowan and Bisk, Yonatan and Schwartz, Roy and Choi, Yejin}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1009}, pages = {93--104}, publisher = {Association for Computational Linguistics}, title = {{SWAG}: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference}, url = {https://aclanthology.org/D18-1009}, year = {2018} } @inproceedings{zellers2019fromrt, author = {Rowan Zellers and Yonatan Bisk and Ali Farhadi and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/ZellersBFC19.bib}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2019, Long Beach, CA, USA, June 16-20, 2019}, doi = {10.1109/CVPR.2019.00688}, pages = {6720--6731}, publisher = {Computer Vision Foundation / {IEEE}}, timestamp = {Mon, 20 Jan 2020 00:00:00 +0100}, title = {From Recognition to Cognition: Visual Commonsense Reasoning}, url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Zellers\_From\_Recognition\_to\_Cognition\_Visual\_Commonsense\_Reasoning\_CVPR\_2019\_paper.html}, year = {2019} } @inproceedings{zellers2019hellaswagca, address = {Florence, Italy}, author = {Zellers, Rowan and Holtzman, Ari and Bisk, Yonatan and Farhadi, Ali and Choi, Yejin}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1472}, pages = {4791--4800}, publisher = {Association for Computational Linguistics}, title = {{H}ella{S}wag: Can a Machine Really Finish Your Sentence?}, url = {https://aclanthology.org/P19-1472}, year = {2019} } @article{zhang2015discriminativesw, author = {Zhang, Yue and Clark, Stephen}, doi = {10.1162/COLI_a_00229}, journal = {Computational Linguistics}, number = {3}, pages = {503--538}, title = {Discriminative Syntax-Based Word Ordering for Text Generation}, url = {https://aclanthology.org/J15-3005}, volume = {41}, year = {2015} } @inproceedings{zhang2018graphco, address = {Brussels, Belgium}, author = {Zhang, Yuhao and Qi, Peng and Manning, Christopher D.}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1244}, pages = {2205--2215}, publisher = {Association for Computational Linguistics}, title = {Graph Convolution over Pruned Dependency Trees Improves Relation Extraction}, url = {https://aclanthology.org/D18-1244}, year = {2018} } @inproceedings{zhang2019conversationgw, address = {Online}, author = {Zhang, Houyu and Liu, Zhenghao and Xiong, Chenyan and Liu, Zhiyuan}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.184}, pages = {2031--2043}, publisher = {Association for Computational Linguistics}, title = {Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs}, url = {https://aclanthology.org/2020.acl-main.184}, year = {2020} } @inproceedings{zhang2020bertscore, author = {Tianyi Zhang and Varsha Kishore and Felix Wu and Kilian Q. Weinberger and Yoav Artzi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ZhangKWWA20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Wed, 03 Jun 2020 01:00:00 +0200}, title = {BERTScore: Evaluating Text Generation with {BERT}}, url = {https://openreview.net/forum?id=SkeHuCVFDr}, year = {2020} } @inproceedings{Zhang2020BERTScoreET, author = {Tianyi Zhang and Varsha Kishore and Felix Wu and Kilian Q. Weinberger and Yoav Artzi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ZhangKWWA20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Wed, 03 Jun 2020 01:00:00 +0200}, title = {BERTScore: Evaluating Text Generation with {BERT}}, url = {https://openreview.net/forum?id=SkeHuCVFDr}, year = {2020} } @article{Zhong2018ImprovingQA, author = {Wanjun Zhong and Duyu Tang and Nan Duan and Ming Zhou and Jiahai Wang and Jian Yin}, journal = {ArXiv preprint}, title = {Improving Question Answering by Commonsense-Based Pre-Training}, url = {https://arxiv.org/abs/1809.03568}, volume = {abs/1809.03568}, year = {2018} } @inproceedings{zhou2017emotionalcm, author = {Hao Zhou and Minlie Huang and Tianyang Zhang and Xiaoyan Zhu and Bing Liu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/ZhouHZZL18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {730--739}, publisher = {{AAAI} Press}, timestamp = {Wed, 08 Jan 2020 00:00:00 +0100}, title = {Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16455}, year = {2018} } @inproceedings{zhou2018commonsenseka, author = {Hao Zhou and Tom Young and Minlie Huang and Haizhou Zhao and Jingfang Xu and Xiaoyan Zhu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/ZhouYHZXZ18.bib}, booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, {IJCAI} 2018, July 13-19, 2018, Stockholm, Sweden}, doi = {10.24963/ijcai.2018/643}, editor = {J{\'{e}}r{\^{o}}me Lang}, pages = {4623--4629}, publisher = {ijcai.org}, timestamp = {Tue, 03 Sep 2019 01:00:00 +0200}, title = {Commonsense Knowledge Aware Conversation Generation with Graph Attention}, url = {https://doi.org/10.24963/ijcai.2018/643}, year = {2018} } @article{zhou2018graph, author = {Zhou, Jie and Cui, Ganqu and Zhang, Zhengyan and Yang, Cheng and Liu, Zhiyuan and Sun, Maosong}, journal = {ArXiv preprint}, title = {Graph Neural Networks: A Review of Methods and Applications}, url = {https://arxiv.org/abs/1812.08434}, volume = {abs/1812.08434}, year = {2018} } @article{Zhu2019TextI, author = {Wanrong Zhu and Zhiting Hu and Eric P. Xing}, journal = {ArXiv preprint}, title = {Text Infilling}, url = {https://arxiv.org/abs/1901.00158}, volume = {abs/1901.00158}, year = {2019} } @inproceedings{NEURIPS2019_f4dd765c, author = {Khurram Javed and Martha White}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/JavedW19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {1818--1828}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Meta-Learning Representations for Continual Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/f4dd765c12f2ef67f98f3558c282a9cd-Abstract.html}, year = {2019} } @article{french1999catastrophic, author = {French, Robert M}, journal = {Trends in cognitive sciences}, number = {4}, pages = {128--135}, publisher = {Elsevier}, title = {Catastrophic forgetting in connectionist networks}, volume = {3}, year = {1999} } @inproceedings{sun2019lamol, author = {Fan{-}Keng Sun and Cheng{-}Hao Ho and Hung{-}Yi Lee}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/SunHL20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{LAMOL:} LAnguage MOdeling for Lifelong Language Learning}, url = {https://openreview.net/forum?id=Skgxcn4YDS}, year = {2020} } @inproceedings{wang2019glue, author = {Alex Wang and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/WangSMHLB19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {{GLUE:} {A} Multi-Task Benchmark and Analysis Platform for Natural Language Understanding}, url = {https://openreview.net/forum?id=rJ4km2R5t7}, year = {2019} } @inproceedings{sun2019fine, author = {Sun, Chi and Qiu, Xipeng and Xu, Yige and Huang, Xuanjing}, booktitle = {China National Conference on Chinese Computational Linguistics}, organization = {Springer}, pages = {194--206}, title = {How to fine-tune BERT for text classification?}, year = {2019} } @inproceedings{xu2019bert, address = {Minneapolis, Minnesota}, author = {Xu, Hu and Liu, Bing and Shu, Lei and Yu, Philip}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1242}, pages = {2324--2335}, publisher = {Association for Computational Linguistics}, title = {{BERT} Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis}, url = {https://aclanthology.org/N19-1242}, year = {2019} } @inproceedings{widmer1993effective, author = {Widmer, Gerhard and Kubat, Miroslav}, booktitle = {European Conference on Machine Learning}, organization = {Springer}, pages = {227--243}, title = {Effective learning in dynamic environments by explicit context tracking}, year = {1993} } @inproceedings{biesialska2020continual, address = {Barcelona, Spain (Online)}, author = {Biesialska, Magdalena and Biesialska, Katarzyna and Costa-juss{\`a}, Marta R.}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, doi = {10.18653/v1/2020.coling-main.574}, pages = {6523--6541}, publisher = {International Committee on Computational Linguistics}, title = {Continual Lifelong Learning in Natural Language Processing: A Survey}, url = {https://aclanthology.org/2020.coling-main.574}, year = {2020} } @inproceedings{sun2019utilizing, address = {Minneapolis, Minnesota}, author = {Sun, Chi and Huang, Luyao and Qiu, Xipeng}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1035}, pages = {380--385}, publisher = {Association for Computational Linguistics}, title = {Utilizing {BERT} for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence}, url = {https://aclanthology.org/N19-1035}, year = {2019} } @inproceedings{NEURIPS2019_4496bf24, author = {Alex Wang and Yada Pruksachatkun and Nikita Nangia and Amanpreet Singh and Julian Michael and Felix Hill and Omer Levy and Samuel R. Bowman}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/WangPNSMHLB19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {3261--3275}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {SuperGLUE: {A} Stickier Benchmark for General-Purpose Language Understanding Systems}, url = {https://proceedings.neurips.cc/paper/2019/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html}, year = {2019} } @inproceedings{yang2019xlnet, author = {Zhilin Yang and Zihang Dai and Yiming Yang and Jaime G. Carbonell and Ruslan Salakhutdinov and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/YangDYCSL19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {5754--5764}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding}, url = {https://proceedings.neurips.cc/paper/2019/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html}, year = {2019} } @inproceedings{linzen2020can, address = {Online}, author = {Linzen, Tal}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.465}, pages = {5210--5217}, publisher = {Association for Computational Linguistics}, title = {How Can We Accelerate Progress Towards Human-like Linguistic Generalization?}, url = {https://aclanthology.org/2020.acl-main.465}, year = {2020} } @inproceedings{devlin2018bert, address = {Minneapolis, Minnesota}, author = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1423}, pages = {4171--4186}, publisher = {Association for Computational Linguistics}, title = {{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding}, url = {https://aclanthology.org/N19-1423}, year = {2019} } @inproceedings{Requeima2019FastAF, author = {James Requeima and Jonathan Gordon and John Bronskill and Sebastian Nowozin and Richard E. Turner}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/Requeima0BNT19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {7957--7968}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes}, url = {https://proceedings.neurips.cc/paper/2019/hash/1138d90ef0a0848a542e57d1595f58ea-Abstract.html}, year = {2019} } @inproceedings{zintgraf2019fast, author = {Luisa M. Zintgraf and Kyriacos Shiarlis and Vitaly Kurin and Katja Hofmann and Shimon Whiteson}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/ZintgrafSKHW19.bib}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, pages = {7693--7702}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 11 Jun 2019 01:00:00 +0200}, title = {Fast Context Adaptation via Meta-Learning}, url = {http://proceedings.mlr.press/v97/zintgraf19a.html}, volume = {97}, year = {2019} } @phdthesis{schmidhuber1987evolutionary, author = {Schmidhuber, J{\""u}rgen}, school = {Technische Universit{\""a}t M{\""u}nchen}, title = {Evolutionary principles in self-referential learning, or on learning how to learn: the meta-meta-... hook}, year = {1987} } @inproceedings{finn2017model, author = {Chelsea Finn and Pieter Abbeel and Sergey Levine}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/FinnAL17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {1126--1135}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks}, url = {http://proceedings.mlr.press/v70/finn17a.html}, volume = {70}, year = {2017} } @inproceedings{Oswald2020ContinualLW, author = {Johannes von Oswald and Christian Henning and Jo{\~{a}}o Sacramento and Benjamin F. Grewe}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/OswaldHSG20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Continual learning with hypernetworks}, url = {https://openreview.net/forum?id=SJgwNerKvB}, year = {2020} } @article{Ye2021ZeroshotLB, author = {Qinyuan Ye and X. Ren}, journal = {ArXiv preprint}, title = {Zero-shot Learning by Generating Task-specific Adapters}, url = {https://arxiv.org/abs/2101.00420}, volume = {abs/2101.00420}, year = {2021} } @article{He2019TaskAC, author = {X. He and Jakub Sygnowski and Alexandre Galashov and Andrei A. Rusu and Y. Teh and Razvan Pascanu}, journal = {ArXiv preprint}, title = {Task Agnostic Continual Learning via Meta Learning}, url = {https://arxiv.org/abs/1906.05201}, volume = {abs/1906.05201}, year = {2019} } @inproceedings{Rajasegaran2020iTAMLAI, author = {Jathushan Rajasegaran and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Mubarak Shah}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/RajasegaranKHKS20.bib}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, doi = {10.1109/CVPR42600.2020.01360}, pages = {13585--13594}, publisher = {{IEEE}}, timestamp = {Tue, 11 Aug 2020 01:00:00 +0200}, title = {iTAML: An Incremental Task-Agnostic Meta-learning Approach}, url = {https://doi.org/10.1109/CVPR42600.2020.01360}, year = {2020} } @inproceedings{Chuang2020LifelongLK, address = {Online}, author = {Chuang, Yung-Sung and Su, Shang-Yu and Chen, Yun-Nung}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.233}, pages = {2914--2924}, publisher = {Association for Computational Linguistics}, title = {Lifelong Language Knowledge Distillation}, url = {https://aclanthology.org/2020.emnlp-main.233}, year = {2020} } @inproceedings{Sun2020LAMOLLM, author = {Fan{-}Keng Sun and Cheng{-}Hao Ho and Hung{-}Yi Lee}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/SunHL20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {{LAMOL:} LAnguage MOdeling for Lifelong Language Learning}, url = {https://openreview.net/forum?id=Skgxcn4YDS}, year = {2020} } @inproceedings{Wang2020EfficientML, address = {Online}, author = {Wang, Zirui and Mehta, Sanket Vaibhav and Poczos, Barnabas and Carbonell, Jaime}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.39}, pages = {535--548}, publisher = {Association for Computational Linguistics}, title = {Efficient Meta Lifelong-Learning with Limited Memory}, url = {https://aclanthology.org/2020.emnlp-main.39}, year = {2020} } @inproceedings{Riemer2019LearningTL, author = {Matthew Riemer and Ignacio Cases and Robert Ajemian and Miao Liu and Irina Rish and Yuhai Tu and Gerald Tesauro}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/RiemerCALRTT19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 12 Sep 2019 01:00:00 +0200}, title = {Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference}, url = {https://openreview.net/forum?id=B1gTShAct7}, year = {2019} } @inproceedings{Jerfel2019ReconcilingMA, author = {Ghassen Jerfel and Erin Grant and Tom Griffiths and Katherine A. Heller}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/JerfelGGH19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {9119--9130}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Reconciling meta-learning and continual learning with online mixtures of tasks}, url = {https://proceedings.neurips.cc/paper/2019/hash/7a9a322cbe0d06a98667fdc5160dc6f8-Abstract.html}, year = {2019} } @inproceedings{Pfeiffer2020AdapterFusionNT, address = {Online}, author = {Pfeiffer, Jonas and Kamath, Aishwarya and R{\""u}ckl{\'e}, Andreas and Cho, Kyunghyun and Gurevych, Iryna}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, pages = {487--503}, publisher = {Association for Computational Linguistics}, title = {{A}dapter{F}usion: Non-Destructive Task Composition for Transfer Learning}, url = {https://aclanthology.org/2021.eacl-main.39}, year = {2021} } @article{robins1995catastrophic, author = {Robins, Anthony}, journal = {Connection Science}, number = {2}, pages = {123--146}, publisher = {Citeseer}, title = {Catastrophic forgetting, rehearsal and pseudorehearsal}, volume = {7}, year = {1995} } @article{gama2014survey, author = {Gama, Jo{\~a}o and {\v{Z}}liobait{\.e}, Indr{\.e} and Bifet, Albert and Pechenizkiy, Mykola and Bouchachia, Abdelhamid}, journal = {CSUR}, number = {4}, pages = {1--37}, publisher = {ACM New York, NY, USA}, title = {A survey on concept drift adaptation}, volume = {46}, year = {2014} } @article{morgenstern2014properties, author = {Morgenstern, Yaniv and Rostami, Mohammad and Purves, Dale}, journal = {Proceedings of the National Academy of Sciences}, number = {Supplement 3}, pages = {10868--10872}, publisher = {National Acad Sciences}, title = {Properties of artificial networks evolved to contend with natural spectra}, volume = {111}, year = {2014} } @article{bolley2007quantitative, author = {Bolley, Fran{\c{c}}ois and Guillin, Arnaud and Villani, C{\'e}dric}, journal = {Probability Theory and Related Fields}, number = {3-4}, pages = {541--593}, publisher = {Springer}, title = {Quantitative concentration inequalities for empirical measures on non-compact spaces}, volume = {137}, year = {2007} } @book{saitoh1997integral, author = {Saitoh, Saburou}, publisher = {CRC Press}, title = {Integral transforms, reproducing kernels and their applications}, volume = {369}, year = {1997} } @article{diek2010, author = {Diekelmann, Susanne and Born, Jan}, journal = {Nature Reviews Neuroscience}, number = {2}, pages = {114}, publisher = {Nature Publishing Group}, title = {The memory function of sleep}, volume = {11}, year = {2010} } @article{rasch2013, author = {Rasch, Bj{\""o}rn and Born, Jan}, journal = {Physiological Reviews}, number = {2}, pages = {681--766}, publisher = {American Physiological Society Bethesda, MD}, title = {About sleep's role in memory}, volume = {93}, year = {2013} } @inproceedings{shin2017continual, author = {Hanul Shin and Jung Kwon Lee and Jaehong Kim and Jiwon Kim}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ShinLKK17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {2990--2999}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Continual Learning with Deep Generative Replay}, url = {https://proceedings.neurips.cc/paper/2017/hash/0efbe98067c6c73dba1250d2beaa81f9-Abstract.html}, year = {2017} } @article{li2018learning, author = {Li, Zhizhong and Hoiem, Derek}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {12}, pages = {2935--2947}, publisher = {IEEE}, title = {Learning without forgetting}, volume = {40}, year = {2018} } @inproceedings{metz2016unrolled, author = {Luke Metz and Ben Poole and David Pfau and Jascha Sohl{-}Dickstein}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/MetzPPS17.bib}, booktitle = {5th International Conference on Learning Representations, {ICLR} 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Unrolled Generative Adversarial Networks}, url = {https://openreview.net/forum?id=BydrOIcle}, year = {2017} } @inproceedings{krizhevsky2012imagenet, author = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/KrizhevskySH12.bib}, booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States}, editor = {Peter L. Bartlett and Fernando C. N. Pereira and Christopher J. C. Burges and L{\'{e}}on Bottou and Kilian Q. Weinberger}, pages = {1106--1114}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {ImageNet Classification with Deep Convolutional Neural Networks}, url = {https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html}, year = {2012} } @inproceedings{rabin2011wasserstein, author = {Rabin, Julien and Peyr{\'e}, Gabriel}, booktitle = {2011 18th IEEE International Conference on Image Processing}, organization = {IEEE}, pages = {1541--1544}, title = {Wasserstein regularization of imaging problem}, year = {2011} } @inproceedings{redko2017theoretical, author = {Redko, Ievgen and Habrard, Amaury and Sebban, Marc}, booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases}, organization = {Springer}, pages = {737--753}, title = {Theoretical analysis of domain adaptation with optimal transport}, year = {2017} } @misc{WinNT, author = {Ryuichiro Hataya}, howpublished = {\url{https://github.com/moskomule/ewc.pytorch}}, note = {[Online; accessed 14-June-2019]}, title = {{EWC} {P}y{T}orch}, year = {2019} } @article{mcinnes2018umap, author = {McInnes, Leland and Healy, John and Melville, James}, journal = {ArXiv preprint}, title = {UMAP: Uniform manifold approximation and projection for dimension reduction}, url = {https://arxiv.org/abs/1802.03426}, volume = {abs/1802.03426}, year = {2018} } @article{courty2017optimal, author = {Courty, Nicolas and Flamary, R{\'e}mi and Tuia, Devis and Rakotomamonjy, Alain}, journal = {IEEE TPAMI}, number = {9}, pages = {1853--1865}, publisher = {IEEE}, title = {Optimal transport for domain adaptation}, volume = {39}, year = {2017} } @phdthesis{bonnotte2013unidimensional, author = {Bonnotte, Nicolas}, school = {Paris 11}, title = {Unidimensional and evolution methods for optimal transportation}, year = {2013} } @article{chen2016lifelong, author = {Chen, Zhiyuan and Liu, Bing}, journal = {Synthesis Lectures on Artificial Intelligence and Machine Learning}, number = {3}, pages = {1--145}, publisher = {Morgan \& Claypool Publishers}, title = {Lifelong machine learning}, volume = {10}, year = {2016} } @book{chomsky2002syntactic, author = {Chomsky, Noam}, publisher = {Walter de Gruyter}, title = {Syntactic structures}, year = {2002} } @book{shalev2014understanding, author = {Shalev-Shwartz, Shai and Ben-David, Shai}, publisher = {Cambridge University Press}, title = {Understanding machine learning: From theory to algorithms}, year = {2014} } @inproceedings{srivastava2017veegan, author = {Akash Srivastava and Lazar Valkov and Chris Russell and Michael U. Gutmann and Charles Sutton}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SrivastavaVRGS17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {3308--3318}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {{VEEGAN:} Reducing Mode Collapse in GANs using Implicit Variational Learning}, url = {https://proceedings.neurips.cc/paper/2017/hash/44a2e0804995faf8d2e3b084a1e2db1d-Abstract.html}, year = {2017} } @inproceedings{roth2017stabilizing, author = {Kevin Roth and Aur{\'{e}}lien Lucchi and Sebastian Nowozin and Thomas Hofmann}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/RothLNH17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {2018--2028}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Stabilizing Training of Generative Adversarial Networks through Regularization}, url = {https://proceedings.neurips.cc/paper/2017/hash/7bccfde7714a1ebadf06c5f4cea752c1-Abstract.html}, year = {2017} } @article{mcclelland1995there, author = {McClelland, James L and McNaughton, Bruce L and O'Reilly, Randall C}, journal = {Psychological Review}, number = {3}, pages = {419}, publisher = {American Psychological Association}, title = {Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory.}, volume = {102}, year = {1995} } @article{widmer1996learning, author = {Widmer, Gerhard and Kubat, Miroslav}, journal = {Machine learning}, number = {1}, pages = {69--101}, publisher = {Springer}, title = {Learning in the presence of concept drift and hidden contexts}, volume = {23}, year = {1996} } @article{gennari1989models, author = {Gennari, John H and Langley, Pat and Fisher, Doug}, journal = {Artificial intelligence}, number = {1-3}, pages = {11--61}, publisher = {Elsevier}, title = {Models of incremental concept formation}, volume = {40}, year = {1989} } @inproceedings{french1991using, author = {French, Robert M}, booktitle = {Proceedings of the 13th annual cognitive science society conference}, pages = {173--178}, title = {Using semi-distributed representations to overcome catastrophic forgetting in connectionist networks}, volume = {1}, year = {1991} } @article{gelbard2008internally, author = {Gelbard-Sagiv, Hagar and Mukamel, Roy and Harel, Michal and Malach, Rafael and Fried, Itzhak}, journal = {Science}, number = {5898}, pages = {96--101}, publisher = {American Association for the Advancement of Science}, title = {Internally generated reactivation of single neurons in human hippocampus during free recall}, volume = {322}, year = {2008} } @inproceedings{kolouri2018sliced, author = {Soheil Kolouri and Gustavo K. Rohde and Heiko Hoffmann}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/KolouriRH18.bib}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, doi = {10.1109/CVPR.2018.00361}, pages = {3427--3436}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 27 Mar 2020 00:00:00 +0100}, title = {Sliced Wasserstein Distance for Learning Gaussian Mixture Models}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Kolouri\_Sliced\_Wasserstein\_Distance\_CVPR\_2018\_paper.html}, year = {2018} } @article{ans1997avoiding, author = {Ans, Bernard and Rousset, St{\'e}phane}, journal = {Comptes Rendus de l'Acad{\'e}mie des Sciences-Series III-Sciences de la Vie}, number = {12}, pages = {989--997}, publisher = {Elsevier}, title = {Avoiding catastrophic forgetting by coupling two reverberating neural networks}, volume = {320}, year = {1997} } @article{hattori2014biologically, author = {Hattori, Motonobu}, journal = {Neurocomputing}, pages = {262--268}, publisher = {Elsevier}, title = {A biologically inspired dual-network memory model for reduction of catastrophic forgetting}, volume = {134}, year = {2014} } @inproceedings{zenke2017continual, author = {Friedemann Zenke and Ben Poole and Surya Ganguli}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/ZenkePG17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {3987--3995}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Continual Learning Through Synaptic Intelligence}, url = {http://proceedings.mlr.press/v70/zenke17a.html}, volume = {70}, year = {2017} } @article{lamprecht2004structural, author = {Lamprecht, Raphael and LeDoux, Joseph}, journal = {Nature Reviews Neuroscience}, number = {1}, pages = {45}, publisher = {Nature Publishing Group}, title = {Structural plasticity and memory}, volume = {5}, year = {2004} } @inproceedings{aljundi2018memory, author = {Aljundi, Rahaf and Babiloni, Francesca and Elhoseiny, Mohamed and Rohrbach, Marcus and Tuytelaars, Tinne}, booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)}, pages = {139--154}, title = {Memory aware synapses: Learning what (not) to forget}, year = {2018} } @inproceedings{isele2018selective, author = {David Isele and Akansel Cosgun}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/IseleC18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {3302--3309}, publisher = {{AAAI} Press}, timestamp = {Mon, 22 Oct 2018 01:00:00 +0200}, title = {Selective Experience Replay for Lifelong Learning}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16054}, year = {2018} } @inproceedings{schaul2015prioritized, author = {Tom Schaul and John Quan and Ioannis Antonoglou and David Silver}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/journals/corr/SchaulQAS15.bib}, booktitle = {4th International Conference on Learning Representations, {ICLR} 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings}, editor = {Yoshua Bengio and Yann LeCun}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Prioritized Experience Replay}, url = {http://arxiv.org/abs/1511.05952}, year = {2016} } @inproceedings{jiang1997semantic, address = {Taipei, Taiwan}, author = {Jiang, Jay J. and Conrath, David W.}, booktitle = {Proceedings of the 10th Research on Computational Linguistics International Conference}, pages = {19--33}, publisher = {The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)}, title = {Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy}, url = {https://aclanthology.org/O97-1002}, year = {1997} } @inproceedings{goodfellow2014generative, author = {Ian J. Goodfellow and Jean Pouget{-}Abadie and Mehdi Mirza and Bing Xu and David Warde{-}Farley and Sherjil Ozair and Aaron C. Courville and Yoshua Bengio}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/GoodfellowPMXWOCB14.bib}, booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada}, editor = {Zoubin Ghahramani and Max Welling and Corinna Cortes and Neil D. Lawrence and Kilian Q. Weinberger}, pages = {2672--2680}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Generative Adversarial Nets}, url = {https://proceedings.neurips.cc/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html}, year = {2014} } @inproceedings{petroni2020kilt, address = {Online}, author = {Petroni, Fabio and Piktus, Aleksandra and Fan, Angela and Lewis, Patrick and Yazdani, Majid and De Cao, Nicola and Thorne, James and Jernite, Yacine and Karpukhin, Vladimir and Maillard, Jean and Plachouras, Vassilis and Rockt{\""a}schel, Tim and Riedel, Sebastian}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.200}, pages = {2523--2544}, publisher = {Association for Computational Linguistics}, title = {{KILT}: a Benchmark for Knowledge Intensive Language Tasks}, url = {https://aclanthology.org/2021.naacl-main.200}, year = {2021} } @book{grossberg2012studies, author = {Grossberg, Stephen T}, publisher = {Springer Science \& Business Media}, title = {Studies of mind and brain: Neural principles of learning, perception, development, cognition, and motor control}, volume = {70}, year = {2012} } @article{kirkpatrick2017overcoming, author = {Kirkpatrick, James and Pascanu, Razvan and Rabinowitz, Neil and Others}, journal = {Proceedings of the national academy of sciences}, number = {13}, pages = {3521--3526}, publisher = {National Acad Sciences}, title = {Overcoming catastrophic forgetting in neural networks}, volume = {114}, year = {2017} } @inproceedings{lecun1990handwritten, author = {LeCun, Yann and Boser, Bernhard and Denker, John and Others}, booktitle = {Advances in Neural Information Processing Systems}, pages = {396--404}, title = {Handwritten digit recognition with a back-propagation network}, year = {1990} } @article{song2000competitive, author = {Song, Sen and Miller, Kenneth D and Abbott, Larry F}, journal = {Nature neuroscience}, number = {9}, pages = {919--926}, title = {Competitive Hebbian learning through spike-timing-dependent synaptic plasticity}, volume = {3}, year = {2000} } @article{hinton1984distributed, author = {Hinton, Geoffrey E and McClelland, James L and Rumelhart, David E}, publisher = {Carnegie Mellon University}, title = {Distributed representations}, year = {1984} } @article{hasson2020direct, author = {Hasson, Uri and Nastase, Samuel A and Goldstein, Ariel}, journal = {Neuron}, number = {3}, pages = {416--434}, publisher = {Elsevier}, title = {Direct fit to nature: An evolutionary perspective on biological and artificial neural networks}, volume = {105}, year = {2020} } @inproceedings{heinen2012using, author = {Heinen, Milton Roberto and Engel, Paulo Martins and Pinto, Rafael C}, booktitle = {The 2012 International Joint Conference on Neural Networks (IJCNN)}, organization = {IEEE}, pages = {1--8}, title = {Using a Gaussian mixture neural network for incremental learning and robotics}, year = {2012} } @article{mcclelland1986parallel, author = {McClelland, James L and Rumelhart, David E and PDP Research Group and others}, journal = {Explorations in the Microstructure of Cognition}, pages = {216--271}, publisher = {MIT Press Cambridge, Ma}, title = {Parallel distributed processing}, volume = {2}, year = {1986} } @inproceedings{rannen2017encoder, author = {Amal Rannen Triki and Rahaf Aljundi and Matthew B. Blaschko and Tinne Tuytelaars}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iccv/TrikiABT17.bib}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2017, Venice, Italy, October 22-29, 2017}, doi = {10.1109/ICCV.2017.148}, pages = {1329--1337}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 27 Dec 2019 00:00:00 +0100}, title = {Encoder Based Lifelong Learning}, url = {https://doi.org/10.1109/ICCV.2017.148}, year = {2017} } @article{mcclelland2003parallel, author = {McClelland, James L and Rogers, Timothy T}, journal = {Nature reviews Neuro.}, number = {4}, pages = {310--322}, title = {The parallel distributed processing approach to semantic cognition}, volume = {4}, year = {2003} } @article{lake2015human, author = {Lake, Brenden M and Salakhutdinov, Ruslan and Tenenbaum, Joshua B}, journal = {Science}, number = {6266}, pages = {1332--1338}, publisher = {American Association for the Advancement of Science}, title = {Human-level concept learning through probabilistic program induction}, volume = {350}, year = {2015} } @article{parisi2019continual, author = {Parisi, German I and Kemker, Ronald and Part, Jose L and Kanan, Christopher and Wermter, Stefan}, journal = {Neural Networks}, publisher = {Elsevier}, title = {Continual lifelong learning with neural networks: A review}, year = {2019} } @inproceedings{snell2017prototypical, author = {Jake Snell and Kevin Swersky and Richard S. Zemel}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/SnellSZ17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {4077--4087}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Prototypical Networks for Few-shot Learning}, url = {https://proceedings.neurips.cc/paper/2017/hash/cb8da6767461f2812ae4290eac7cbc42-Abstract.html}, year = {2017} } @article{arjovsky2017wasserstein, author = {Arjovsky, Martin and Chintala, Soumith and Bottou, L{\'e}on}, journal = {ArXiv preprint}, title = {Wasserstein gan}, url = {https://arxiv.org/abs/1701.07875}, volume = {abs/1701.07875}, year = {2017} } @article{bonneel2015sliced, author = {Bonneel, Nicolas and Rabin, Julien and Peyr{\'e}, Gabriel and Pfister, Hanspeter}, journal = {Journal of Math. Imag. and Vision}, number = {1}, pages = {22--45}, publisher = {Springer}, title = {Sliced and radon wasserstein barycenters of measures}, volume = {51}, year = {2015} } @inproceedings{ashtiani2018nearly, author = {Hassan Ashtiani and Shai Ben{-}David and Nicholas J. A. Harvey and Christopher Liaw and Abbas Mehrabian and Yaniv Plan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/AshtianiBHLMP18.bib}, booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr{\'{e}}al, Canada}, editor = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicol{\`{o}} Cesa{-}Bianchi and Roman Garnett}, pages = {3416--3425}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes}, url = {https://proceedings.neurips.cc/paper/2018/hash/70ece1e1e0931919438fcfc6bd5f199c-Abstract.html}, year = {2018} } @inproceedings{globerson2006metric, author = {Amir Globerson and Sam T. Roweis}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/GlobersonR05.bib}, booktitle = {Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, {NIPS} 2005, December 5-8, 2005, Vancouver, British Columbia, Canada]}, pages = {451--458}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Metric Learning by Collapsing Classes}, url = {https://proceedings.neurips.cc/paper/2005/hash/ad8e88c0f76fa4fc8e5474384142a00a-Abstract.html}, year = {2005} } @article{mangal2007analysis, author = {Mangal, Manish and Singh, Manu Pratap}, journal = {International Journal on Artificial Intelligence Tools}, number = {01}, pages = {111--120}, publisher = {World Scientific}, title = {Analysis of multidimensional XOR classification problem with evolutionary feedforward neural networks}, volume = {16}, year = {2007} } @incollection{mccloskey1989catastrophic, author = {McCloskey, Michael and Cohen, Neal J}, booktitle = {Psychology of learning and motivation}, pages = {109--165}, publisher = {Elsevier}, title = {Catastrophic interference in connectionist networks: The sequential learning problem}, volume = {24}, year = {1989} } @article{saxe2019mathematical, author = {Saxe, Andrew M and McClelland, James L and Ganguli, Surya}, journal = {Proceedings of the National Academy of Sciences}, pages = {201820226}, publisher = {National Acad Sciences}, title = {A mathematical theory of semantic development in deep neural networks}, year = {2019} } @article{longcamp2005influence, author = {Longcamp, Marieke and Zerbato-Poudou, Marie-Th{\'e}r{\`e}se and Velay, Jean-Luc}, journal = {Acta psychologica}, number = {1}, pages = {67--79}, publisher = {Elsevier}, title = {The influence of writing practice on letter recognition in preschool children: A comparison between handwriting and typing}, volume = {119}, year = {2005} } @inproceedings{rostami2019Complementary, author = {Mohammad Rostami and Soheil Kolouri and Praveen K. Pilly}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/ijcai/RostamiKP19.bib}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, doi = {10.24963/ijcai.2019/463}, editor = {Sarit Kraus}, pages = {3339--3345}, publisher = {ijcai.org}, timestamp = {Tue, 20 Aug 2019 01:00:00 +0200}, title = {Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay}, url = {https://doi.org/10.24963/ijcai.2019/463}, year = {2019} } @inproceedings{rebuffi2017icarl, author = {Sylvestre{-}Alvise Rebuffi and Alexander Kolesnikov and Georg Sperl and Christoph H. Lampert}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/RebuffiKSL17.bib}, booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2017, Honolulu, HI, USA, July 21-26, 2017}, doi = {10.1109/CVPR.2017.587}, pages = {5533--5542}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 20 Nov 2020 00:00:00 +0100}, title = {iCaRL: Incremental Classifier and Representation Learning}, url = {https://doi.org/10.1109/CVPR.2017.587}, year = {2017} } @inproceedings{kemker2017fearnet, author = {Ronald Kemker and Christopher Kanan}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/KemkerK18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {FearNet: Brain-Inspired Model for Incremental Learning}, url = {https://openreview.net/forum?id=SJ1Xmf-Rb}, year = {2018} } @inproceedings{castro2018end, author = {Castro, Francisco M and Mar{\'\i}n-Jim{\'e}nez, Manuel J and Guil, Nicol{\'a}s and Schmid, Cordelia and Alahari, Karteek}, booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)}, pages = {233--248}, title = {End-to-end incremental learning}, year = {2018} } @article{hinton2015distilling, author = {Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff}, journal = {ArXiv preprint}, title = {Distilling the knowledge in a neural network}, url = {https://arxiv.org/abs/1503.02531}, volume = {abs/1503.02531}, year = {2015} } @article{roy2020tree, author = {Roy, Deboleena and Panda, Priyadarshini and Roy, Kaushik}, journal = {Neural Networks}, pages = {148--160}, publisher = {Elsevier}, title = {Tree-CNN: a hierarchical deep CNN for incremental learning}, volume = {121}, year = {2020} } @article{sarwar2019incremental, author = {Sarwar, Syed Shakib and Ankit, Aayush and Roy, Kaushik}, journal = {IEEE Access}, publisher = {IEEE}, title = {Incremental learning in deep convolutional neural networks using partial network sharing}, year = {2019} } @article{li2017learning, author = {Li, Zhizhong and Hoiem, Derek}, journal = {IEEE transactions on pattern analysis and machine intelligence}, number = {12}, pages = {2935--2947}, publisher = {IEEE}, title = {Learning without forgetting}, volume = {40}, year = {2017} } @inproceedings{javed2018revisiting, author = {Javed, Khurram and Shafait, Faisal}, booktitle = {Asian Conference on Computer Vision}, organization = {Springer}, pages = {3--17}, title = {Revisiting distillation and incremental classifier learning}, year = {2018} } @inproceedings{he2018overcoming, author = {Xu He and Herbert Jaeger}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/HeJ18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation}, url = {https://openreview.net/forum?id=B1al7jg0b}, year = {2018} } @inproceedings{lee2017overcoming, author = {Sang{-}Woo Lee and Jin{-}Hwa Kim and Jaehyun Jun and Jung{-}Woo Ha and Byoung{-}Tak Zhang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/LeeKJHZ17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {4652--4662}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Overcoming Catastrophic Forgetting by Incremental Moment Matching}, url = {https://proceedings.neurips.cc/paper/2017/hash/f708f064faaf32a43e4d3c784e6af9ea-Abstract.html}, year = {2017} } @inproceedings{wu2018memory, author = {Chenshen Wu and Luis Herranz and Xialei Liu and Yaxing Wang and Joost van de Weijer and Bogdan Raducanu}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/WuHLWWR18.bib}, booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr{\'{e}}al, Canada}, editor = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicol{\`{o}} Cesa{-}Bianchi and Roman Garnett}, pages = {5966--5976}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Memory Replay GANs: Learning to Generate New Categories without Forgetting}, url = {https://proceedings.neurips.cc/paper/2018/hash/a57e8915461b83adefb011530b711704-Abstract.html}, year = {2018} } @article{zeng2019continual, author = {Zeng, Guanxiong and Chen, Yang and Cui, Bo and Yu, Shan}, journal = {Nature Machine Intelligence}, number = {8}, pages = {364--372}, publisher = {Nature Publishing Group}, title = {Continual learning of context-dependent processing in neural networks}, volume = {1}, year = {2019} } @inproceedings{aljundi2019gradient, author = {Rahaf Aljundi and Min Lin and Baptiste Goujaud and Yoshua Bengio}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/AljundiLGB19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {11816--11825}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Gradient based sample selection for online continual learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/e562cd9c0768d5464b64cf61da7fc6bb-Abstract.html}, year = {2019} } @inproceedings{lopez2017gradient, author = {David Lopez{-}Paz and Marc'Aurelio Ranzato}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/Lopez-PazR17.bib}, booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, {USA}}, editor = {Isabelle Guyon and Ulrike von Luxburg and Samy Bengio and Hanna M. Wallach and Rob Fergus and S. V. N. Vishwanathan and Roman Garnett}, pages = {6467--6476}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Gradient Episodic Memory for Continual Learning}, url = {https://proceedings.neurips.cc/paper/2017/hash/f87522788a2be2d171666752f97ddebb-Abstract.html}, year = {2017} } @article{zenke2017temporal, author = {Zenke, Friedemann and Gerstner, Wulfram and Ganguli, Surya}, journal = {Curr. opinion in neuro.}, pages = {166--176}, publisher = {Elsevier}, title = {The temporal paradox of Hebbian learning and homeostatic plasticity}, volume = {43}, year = {2017} } @article{van2020brain, author = {van de Ven, Gido M and Siegelmann, Hava T and Tolias, Andreas S}, journal = {Nature communications}, number = {1}, pages = {1--14}, publisher = {Nature Publishing Group}, title = {Brain-inspired replay for continual learning with artificial neural networks}, volume = {11}, year = {2020} } @inproceedings{vajjala-lucic-2018-onestopenglish, address = {New Orleans, Louisiana}, author = {Vajjala, Sowmya and Lu{\v{c}}i{\'c}, Ivana}, booktitle = {Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications}, doi = {10.18653/v1/W18-0535}, pages = {297--304}, publisher = {Association for Computational Linguistics}, title = {{O}ne{S}top{E}nglish corpus: A new corpus for automatic readability assessment and text simplification}, url = {https://aclanthology.org/W18-0535}, year = {2018} } @inproceedings{pang-lee-2005-seeing, address = {Ann Arbor, Michigan}, author = {Pang, Bo and Lee, Lillian}, booktitle = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics ({ACL}{'}05)}, doi = {10.3115/1219840.1219855}, pages = {115--124}, publisher = {Association for Computational Linguistics}, title = {Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales}, url = {https://aclanthology.org/P05-1015}, year = {2005} } @inproceedings{cohan-etal-2019-structural, address = {Minneapolis, Minnesota}, author = {Cohan, Arman and Ammar, Waleed and van Zuylen, Madeleine and Cady, Field}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1361}, pages = {3586--3596}, publisher = {Association for Computational Linguistics}, title = {Structural Scaffolds for Citation Intent Classification in Scientific Publications}, url = {https://aclanthology.org/N19-1361}, year = {2019} } @inproceedings{marelli-etal-2014-sick, address = {Reykjavik, Iceland}, author = {Marelli, Marco and Menini, Stefano and Baroni, Marco and Bentivogli, Luisa and Bernardi, Raffaella and Zamparelli, Roberto}, booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)}, pages = {216--223}, publisher = {European Language Resources Association (ELRA)}, title = {A {SICK} cure for the evaluation of compositional distributional semantic models}, url = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/363_Paper.pdf}, year = {2014} } @article{montague1970universal, author = {Montague, Richard}, journal = {1974}, pages = {222--46}, title = {Universal grammar}, year = {1970} } @article{rusu2016progressive, author = {Rusu, A. A. and Rabinowitz, N. C. and Desjardins, G. and Soyer, H. and Kirkpatrick, J. and Kavukcuoglu, K. and Pascanu, R. and Hadsell, R.}, journal = {ArXiv preprint}, title = {Progressive neural networks}, url = {https://arxiv.org/abs/1606.04671}, volume = {abs/1606.04671}, year = {2016} } @article{rasooli-tetrault-2015, author = {Mohammad Sadegh Rasooli and Joel R. Tetreault}, journal = {ArXiv preprint}, title = {Yara Parser: {A} Fast and Accurate Dependency Parser}, url = {https://arxiv.org/abs/1503.06733}, volume = {abs/1503.06733}, year = {2015} } @inproceedings{Bansal2020LearningTF, address = {Barcelona, Spain (Online)}, author = {Bansal, Trapit and Jha, Rishikesh and McCallum, Andrew}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, doi = {10.18653/v1/2020.coling-main.448}, pages = {5108--5123}, publisher = {International Committee on Computational Linguistics}, title = {Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks}, url = {https://aclanthology.org/2020.coling-main.448}, year = {2020} } @inproceedings{lewis-etal-2020-bart, address = {Online}, author = {Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Veselin and Zettlemoyer, Luke}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.703}, pages = {7871--7880}, publisher = {Association for Computational Linguistics}, title = {{BART}: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, url = {https://aclanthology.org/2020.acl-main.703}, year = {2020} } @inproceedings{Finn2017ModelAgnosticMF, author = {Chelsea Finn and Pieter Abbeel and Sergey Levine}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/FinnAL17.bib}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, pages = {1126--1135}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks}, url = {http://proceedings.mlr.press/v70/finn17a.html}, volume = {70}, year = {2017} } @inproceedings{Houlsby2019ParameterEfficientTL, author = {Neil Houlsby and Andrei Giurgiu and Stanislaw Jastrzebski and Bruna Morrone and Quentin de Laroussilhe and Andrea Gesmundo and Mona Attariyan and Sylvain Gelly}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/HoulsbyGJMLGAG19.bib}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, pages = {2790--2799}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Tue, 11 Jun 2019 01:00:00 +0200}, title = {Parameter-Efficient Transfer Learning for {NLP}}, url = {http://proceedings.mlr.press/v97/houlsby19a.html}, volume = {97}, year = {2019} } @article{mccann2018natural, author = {McCann, Bryan and Keskar, Nitish Shirish and Xiong, Caiming and Socher, Richard}, journal = {ArXiv preprint}, title = {The natural language decathlon: Multitask learning as question answering}, url = {https://arxiv.org/abs/1806.08730}, volume = {abs/1806.08730}, year = {2018} } @inproceedings{dAutume2019EpisodicMI, author = {Cyprien de Masson d'Autume and Sebastian Ruder and Lingpeng Kong and Dani Yogatama}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/dAutumeRKY19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {13122--13131}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Episodic Memory in Lifelong Language Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/f8d2e80c1458ea2501f98a2cafadb397-Abstract.html}, year = {2019} } @inproceedings{rusu2018metalearning, author = {Andrei A. Rusu and Dushyant Rao and Jakub Sygnowski and Oriol Vinyals and Razvan Pascanu and Simon Osindero and Raia Hadsell}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/RusuRSVPOH19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Meta-Learning with Latent Embedding Optimization}, url = {https://openreview.net/forum?id=BJgklhAcK7}, year = {2019} } @inproceedings{huang2021continual, address = {Online}, author = {Huang, Yufan and Zhang, Yanzhe and Chen, Jiaao and Wang, Xuezhi and Yang, Diyi}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.218}, pages = {2736--2746}, publisher = {Association for Computational Linguistics}, title = {Continual Learning for Text Classification with Information Disentanglement Based Regularization}, url = {https://aclanthology.org/2021.naacl-main.218}, year = {2021} } @article{Yogatama2019LearningAE, author = {Dani Yogatama and Cyprien de Masson d'Autume and Jerome Connor and Tom{\'a}s Kocisk{\'y} and Mike Chrzanowski and Lingpeng Kong and A. Lazaridou and Wang Ling and L. Yu and Chris Dyer and P. Blunsom}, journal = {ArXiv preprint}, title = {Learning and Evaluating General Linguistic Intelligence}, url = {https://arxiv.org/abs/1901.11373}, volume = {abs/1901.11373}, year = {2019} } @inproceedings{Brown2020LanguageMA, author = {Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert{-}Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Language Models are Few-Shot Learners}, url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html}, year = {2020} } @inproceedings{Gao2020MakingPL, address = {Online}, author = {Gao, Tianyu and Fisch, Adam and Chen, Danqi}, booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, doi = {10.18653/v1/2021.acl-long.295}, pages = {3816--3830}, publisher = {Association for Computational Linguistics}, title = {Making Pre-trained Language Models Better Few-shot Learners}, url = {https://aclanthology.org/2021.acl-long.295}, year = {2021} } @article{Raffel2020ExploringTL, author = {Colin Raffel and Noam M. Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and W. Li and Peter J. Liu}, journal = {ArXiv preprint}, title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer}, url = {https://arxiv.org/abs/1910.10683}, volume = {abs/1910.10683}, year = {2019} } @inproceedings{ha2016hypernetworks, author = {David Ha and Andrew M. Dai and Quoc V. Le}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/HaDL17.bib}, booktitle = {5th International Conference on Learning Representations, {ICLR} 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {HyperNetworks}, url = {https://openreview.net/forum?id=rkpACe1lx}, year = {2017} } @inproceedings{Gidaris2018DynamicFV, author = {Spyros Gidaris and Nikos Komodakis}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/cvpr/GidarisK18.bib}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, doi = {10.1109/CVPR.2018.00459}, pages = {4367--4375}, publisher = {{IEEE} Computer Society}, timestamp = {Wed, 06 Feb 2019 00:00:00 +0100}, title = {Dynamic Few-Shot Visual Learning Without Forgetting}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Gidaris\_Dynamic\_Few-Shot\_Visual\_CVPR\_2018\_paper.html}, year = {2018} } @inproceedings{Nguyen2018VariationalCL, author = {Cuong V. Nguyen and Yingzhen Li and Thang D. Bui and Richard E. Turner}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/NguyenLBT18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Variational Continual Learning}, url = {https://openreview.net/forum?id=BkQqq0gRb}, year = {2018} } @inproceedings{wang2019sentence, address = {Minneapolis, Minnesota}, author = {Wang, Hong and Xiong, Wenhan and Yu, Mo and Guo, Xiaoxiao and Chang, Shiyu and Wang, William Yang}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1086}, pages = {796--806}, publisher = {Association for Computational Linguistics}, title = {Sentence Embedding Alignment for Lifelong Relation Extraction}, url = {https://aclanthology.org/N19-1086}, year = {2019} } @inproceedings{caccia2020online, author = {Massimo Caccia and Pau Rodr{\'{\i}}guez and Oleksiy Ostapenko and Fabrice Normandin and Min Lin and Lucas Page{-}Caccia and Issam Hadj Laradji and Irina Rish and Alexandre Lacoste and David V{\'{a}}zquez and Laurent Charlin}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/CacciaRONLPLRLV20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Online Fast Adaptation and Knowledge Accumulation {(OSAKA):} a New Approach to Continual Learning}, url = {https://proceedings.neurips.cc/paper/2020/hash/c0a271bc0ecb776a094786474322cb82-Abstract.html}, year = {2020} } @article{antoniou2020defining, author = {Antoniou, Antreas and Patacchiola, Massimiliano and Ochal, Mateusz and Storkey, Amos}, journal = {ArXiv preprint}, title = {Defining benchmarks for continual few-shot learning}, url = {https://arxiv.org/abs/2004.11967}, volume = {abs/2004.11967}, year = {2020} } @inproceedings{chatterjee-etal-2019-semeval, address = {Minneapolis, Minnesota, USA}, author = {Chatterjee, Ankush and Narahari, Kedhar Nath and Joshi, Meghana and Agrawal, Puneet}, booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation}, doi = {10.18653/v1/S19-2005}, pages = {39--48}, publisher = {Association for Computational Linguistics}, title = {{S}em{E}val-2019 Task 3: {E}mo{C}ontext Contextual Emotion Detection in Text}, url = {https://aclanthology.org/S19-2005}, year = {2019} } @inproceedings{saravia-etal-2018-carer, address = {Brussels, Belgium}, author = {Saravia, Elvis and Liu, Hsien-Chi Toby and Huang, Yen-Hao and Wu, Junlin and Chen, Yi-Shin}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1404}, pages = {3687--3697}, publisher = {Association for Computational Linguistics}, title = {{CARER}: Contextualized Affect Representations for Emotion Recognition}, url = {https://aclanthology.org/D18-1404}, year = {2018} } @inproceedings{williams-etal-2018-broad, address = {New Orleans, Louisiana}, author = {Williams, Adina and Nangia, Nikita and Bowman, Samuel}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1101}, pages = {1112--1122}, publisher = {Association for Computational Linguistics}, title = {A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference}, url = {https://aclanthology.org/N18-1101}, year = {2018} } @inproceedings{dolan-brockett-2005-automatically, author = {Dolan, William B. and Brockett, Chris}, booktitle = {Proceedings of the Third International Workshop on Paraphrasing ({IWP}2005)}, title = {Automatically Constructing a Corpus of Sentential Paraphrases}, url = {https://aclanthology.org/I05-5002}, year = {2005} } @inproceedings{socher-etal-2013-recursive, address = {Seattle, Washington, USA}, author = {Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher}, booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing}, pages = {1631--1642}, publisher = {Association for Computational Linguistics}, title = {Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank}, url = {https://aclanthology.org/D13-1170}, year = {2013} } @inproceedings{rajpurkar-etal-2016-squad, address = {Austin, Texas}, author = {Rajpurkar, Pranav and Zhang, Jian and Lopyrev, Konstantin and Liang, Percy}, booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D16-1264}, pages = {2383--2392}, publisher = {Association for Computational Linguistics}, title = {{SQ}u{AD}: 100,000+ Questions for Machine Comprehension of Text}, url = {https://aclanthology.org/D16-1264}, year = {2016} } @inproceedings{maas-etal-2011-learning, address = {Portland, Oregon, USA}, author = {Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher}, booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies}, pages = {142--150}, publisher = {Association for Computational Linguistics}, title = {Learning Word Vectors for Sentiment Analysis}, url = {https://aclanthology.org/P11-1015}, year = {2011} } @inproceedings{faruqui-pado-2011-thou, address = {Portland, Oregon, USA}, author = {Faruqui, Manaal and Pad{\'o}, Sebastian}, booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies}, pages = {467--472}, publisher = {Association for Computational Linguistics}, title = {{``}{I} Thou Thee, Thou Traitor{''}: Predicting Formal vs. Informal Address in {E}nglish Literature}, url = {https://aclanthology.org/P11-2082}, year = {2011} } @inproceedings{thorne-etal-2017-fake, address = {Copenhagen, Denmark}, author = {Thorne, James and Chen, Mingjie and Myrianthous, Giorgos and Pu, Jiashu and Wang, Xiaoxuan and Vlachos, Andreas}, booktitle = {Proceedings of the 2017 {EMNLP} Workshop: Natural Language Processing meets Journalism}, doi = {10.18653/v1/W17-4214}, pages = {80--83}, publisher = {Association for Computational Linguistics}, title = {Fake news stance detection using stacked ensemble of classifiers}, url = {https://aclanthology.org/W17-4214}, year = {2017} } @inproceedings{vajjala-banerjee-2017-study, address = {Copenhagen, Denmark}, author = {Vajjala, Sowmya and Banerjee, Sagnik}, booktitle = {Proceedings of the 12th Workshop on Innovative Use of {NLP} for Building Educational Applications}, doi = {10.18653/v1/W17-5026}, pages = {240--248}, publisher = {Association for Computational Linguistics}, title = {A study of N-gram and Embedding Representations for Native Language Identification}, url = {https://aclanthology.org/W17-5026}, year = {2017} } @inproceedings{zhang-etal-2019-paws, address = {Minneapolis, Minnesota}, author = {Zhang, Yuan and Baldridge, Jason and He, Luheng}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1131}, pages = {1298--1308}, publisher = {Association for Computational Linguistics}, title = {{PAWS}: Paraphrase Adversaries from Word Scrambling}, url = {https://aclanthology.org/N19-1131}, year = {2019} } @inproceedings{pilehvar-camacho-collados-2019-wic, address = {Minneapolis, Minnesota}, author = {Pilehvar, Mohammad Taher and Camacho-Collados, Jose}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1128}, pages = {1267--1273}, publisher = {Association for Computational Linguistics}, title = {{W}i{C}: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations}, url = {https://aclanthology.org/N19-1128}, year = {2019} } @inproceedings{li-roth-2002-learning, author = {Li, Xin and Roth, Dan}, booktitle = {{COLING} 2002: The 19th International Conference on Computational Linguistics}, title = {Learning Question Classifiers}, url = {https://aclanthology.org/C02-1150}, year = {2002} } @inproceedings{hovy-etal-2001-toward, author = {Hovy, Eduard and Gerber, Laurie and Hermjakob, Ulf and Lin, Chin-Yew and Ravichandran, Deepak}, booktitle = {Proceedings of the First International Conference on Human Language Technology Research}, title = {Toward Semantics-Based Answer Pinpointing}, url = {https://aclanthology.org/H01-1069}, year = {2001} } @inproceedings{yang-etal-2015-wikiqa, address = {Lisbon, Portugal}, author = {Yang, Yi and Yih, Wen-tau and Meek, Christopher}, booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D15-1237}, pages = {2013--2018}, publisher = {Association for Computational Linguistics}, title = {{W}iki{QA}: A Challenge Dataset for Open-Domain Question Answering}, url = {https://aclanthology.org/D15-1237}, year = {2015} } @inproceedings{faruqui-das-2018-identifying, address = {Brussels, Belgium}, author = {Faruqui, Manaal and Das, Dipanjan}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/D18-1091}, pages = {798--803}, publisher = {Association for Computational Linguistics}, title = {Identifying Well-formed Natural Language Questions}, url = {https://aclanthology.org/D18-1091}, year = {2018} } @inproceedings{thorne-etal-2018-fever, address = {New Orleans, Louisiana}, author = {Thorne, James and Vlachos, Andreas and Christodoulopoulos, Christos and Mittal, Arpit}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1074}, pages = {809--819}, publisher = {Association for Computational Linguistics}, title = {{FEVER}: a Large-scale Dataset for Fact Extraction and {VER}ification}, url = {https://aclanthology.org/N18-1074}, year = {2018} } @inproceedings{wang-2017-liar, address = {Vancouver, Canada}, author = {Wang, William Yang}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, doi = {10.18653/v1/P17-2067}, pages = {422--426}, publisher = {Association for Computational Linguistics}, title = {{``}Liar, Liar Pants on Fire{''}: A New Benchmark Dataset for Fake News Detection}, url = {https://aclanthology.org/P17-2067}, year = {2017} } @article{GURULINGAPPA2012885, abstract = {A significant amount of information about drug-related safety issues such as adverse effects are published in medical case reports that can only be explored by human readers due to their unstructured nature. The work presented here aims at generating a systematically annotated corpus that can support the development and validation of methods for the automatic extraction of drug-related adverse effects from medical case reports. The documents are systematically double annotated in various rounds to ensure consistent annotations. The annotated documents are finally harmonized to generate representative consensus annotations. In order to demonstrate an example use case scenario, the corpus was employed to train and validate models for the classification of informative against the non-informative sentences. A Maximum Entropy classifier trained with simple features and evaluated by 10-fold cross-validation resulted in the F1 score of 0.70 indicating a potential useful application of the corpus.}, author = {Harsha Gurulingappa and Abdul Mateen Rajput and Angus Roberts and Juliane Fluck and Martin Hofmann-Apitius and Luca Toldo}, doi = {https://doi.org/10.1016/j.jbi.2012.04.008}, issn = {1532-0464}, journal = {Journal of Biomedical Informatics}, keywords = {Adverse drug effect, Benchmark corpus, Annotation, Harmonization, Sentence classification}, note = {Text Mining and Natural Language Processing in Pharmacogenomics}, number = {5}, pages = {885-892}, title = {Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports}, url = {https://www.sciencedirect.com/science/article/pii/S1532046412000615}, volume = {45}, year = {2012} } @article{bartolo-etal-2020-beat, author = {Bartolo, Max and Roberts, Alastair and Welbl, Johannes and Riedel, Sebastian and Stenetorp, Pontus}, doi = {10.1162/tacl_a_00338}, journal = {Transactions of the Association for Computational Linguistics}, pages = {662--678}, title = {Beat the {AI}: Investigating Adversarial Human Annotation for Reading Comprehension}, url = {https://aclanthology.org/2020.tacl-1.43}, volume = {8}, year = {2020} } @article{Clark2018ThinkYH, author = {Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord}, journal = {ArXiv preprint}, title = {Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge}, url = {https://arxiv.org/abs/1803.05457}, volume = {abs/1803.05457}, year = {2018} } @inproceedings{McAuley2013HiddenFA, author = {Julian J. McAuley and Jure Leskovec}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/recsys/McAuleyL13.bib}, booktitle = {Seventh {ACM} Conference on Recommender Systems, RecSys '13, Hong Kong, China, October 12-16, 2013}, doi = {10.1145/2507157.2507163}, editor = {Qiang Yang and Irwin King and Qing Li and Pearl Pu and George Karypis}, pages = {165--172}, publisher = {{ACM}}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, title = {Hidden factors and hidden topics: understanding rating dimensions with review text}, url = {https://doi.org/10.1145/2507157.2507163}, year = {2013} } @inproceedings{nie-etal-2020-adversarial, address = {Online}, author = {Nie, Yixin and Williams, Adina and Dinan, Emily and Bansal, Mohit and Weston, Jason and Kiela, Douwe}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.441}, pages = {4885--4901}, publisher = {Association for Computational Linguistics}, title = {Adversarial {NLI}: A New Benchmark for Natural Language Understanding}, url = {https://aclanthology.org/2020.acl-main.441}, year = {2020} } @inproceedings{app-review, authors = {Grano, Giovanni ahd Di Sorbo, Andrea and Mercaldo, Francesco and Visaggio, Corrado A and Canfora, Gerardo and Panichella, Sebastiano}, title = {Software Applications User Reviews}, year = {2017} } @inproceedings{bhagavatula2020abductive, author = {Chandra Bhagavatula and Ronan Le Bras and Chaitanya Malaviya and Keisuke Sakaguchi and Ari Holtzman and Hannah Rashkin and Doug Downey and Wen{-}tau Yih and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/BhagavatulaBMSH20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {Abductive Commonsense Reasoning}, url = {https://openreview.net/forum?id=Byg1v1HKDB}, year = {2020} } @inproceedings{Othman2012EnglishASLGP, author = {A. Othman and M. Jemni}, title = {English-ASL Gloss Parallel Corpus 2012: ASLG-PC12}, year = {2012} } @inproceedings{pappas-etal-2020-biomrc, address = {Online}, author = {Pappas, Dimitris and Stavropoulos, Petros and Androutsopoulos, Ion and McDonald, Ryan}, booktitle = {Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing}, doi = {10.18653/v1/2020.bionlp-1.15}, pages = {140--149}, publisher = {Association for Computational Linguistics}, title = {{B}io{MRC}: A Dataset for Biomedical Machine Reading Comprehension}, url = {https://aclanthology.org/2020.bionlp-1.15}, year = {2020} } @article{warstadt2019blimp, author = {Warstadt, Alex and Parrish, Alicia and Liu, Haokun and Mohananey, Anhad and Peng, Wei and Wang, Sheng-Fu and Bowman, Samuel R.}, doi = {10.1162/tacl_a_00321}, journal = {Transactions of the Association for Computational Linguistics}, pages = {377--392}, title = {{BL}i{MP}: The Benchmark of Linguistic Minimal Pairs for {E}nglish}, url = {https://aclanthology.org/2020.tacl-1.25}, volume = {8}, year = {2020} } @article{wolfson-etal-2020-break, author = {Wolfson, Tomer and Geva, Mor and Gupta, Ankit and Gardner, Matt and Goldberg, Yoav and Deutch, Daniel and Berant, Jonathan}, doi = {10.1162/tacl_a_00309}, journal = {Transactions of the Association for Computational Linguistics}, pages = {183--198}, title = {Break It Down: A Question Understanding Benchmark}, url = {https://aclanthology.org/2020.tacl-1.13}, volume = {8}, year = {2020} } @inproceedings{louis-etal-2020-id, address = {Online}, author = {Louis, Annie and Roth, Dan and Radlinski, Filip}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.601}, pages = {7411--7425}, publisher = {Association for Computational Linguistics}, title = {{``}{I}{'}d rather just go to bed{''}: Understanding Indirect Answers}, url = {https://aclanthology.org/2020.emnlp-main.601}, year = {2020} } @article{Diggelmann2020CLIMATEFEVERAD, author = {T. Diggelmann and Jordan L. Boyd-Graber and Jannis Bulian and Massimiliano Ciaramita and Markus Leippold}, journal = {ArXiv preprint}, title = {CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims}, url = {https://arxiv.org/abs/2012.00614}, volume = {abs/2012.00614}, year = {2020} } @inproceedings{lin-etal-2020-commongen, address = {Online}, author = {Lin, Bill Yuchen and Zhou, Wangchunshu and Shen, Ming and Zhou, Pei and Bhagavatula, Chandra and Choi, Yejin and Ren, Xiang}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.165}, pages = {1823--1840}, publisher = {Association for Computational Linguistics}, title = {{C}ommon{G}en: A Constrained Text Generation Challenge for Generative Commonsense Reasoning}, url = {https://aclanthology.org/2020.findings-emnlp.165}, year = {2020} } @inproceedings{zhang-etal-2020-semi, address = {Barcelona, Spain (Online)}, author = {Zhang, Hao and Ro, Jae and Sproat, Richard}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics}, doi = {10.18653/v1/2020.coling-main.411}, pages = {4667--4675}, publisher = {International Committee on Computational Linguistics}, title = {Semi-supervised {URL} Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities}, url = {https://aclanthology.org/2020.coling-main.411}, year = {2020} } @inproceedings{nangia-etal-2020-crows, address = {Online}, author = {Nangia, Nikita and Vania, Clara and Bhalerao, Rasika and Bowman, Samuel R.}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.154}, pages = {1953--1967}, publisher = {Association for Computational Linguistics}, title = {{C}row{S}-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models}, url = {https://aclanthology.org/2020.emnlp-main.154}, year = {2020} } @article{Lehmann2015DBpediaA, author = {Jens Lehmann and Robert Isele and Max Jakob and Anja Jentzsch and D. Kontokostas and Pablo N. Mendes and Sebastian Hellmann and M. Morsey and Patrick van Kleef and S. Auer and C. Bizer}, journal = {Semantic Web}, pages = {167-195}, title = {DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia}, volume = {6}, year = {2015} } @article{dusek.etal2020:csl, archiveprefix = {arXiv}, author = {Du{\v{s}}ek, Ond\v{r}ej and Novikova, Jekaterina and Rieser, Verena}, doi = {10.1016/j.csl.2019.06.009}, eprint = {1901.11528}, eprinttype = {arxiv}, journal = {Computer Speech \& Language}, pages = {123--156}, title = {Evaluating the {{State}}-of-the-{{Art}} of {{End}}-to-{{End Natural Language Generation}}: {{The E2E NLG Challenge}}}, volume = {59}, year = {2020} } @inproceedings{dusek-etal-2019-semantic, address = {Tokyo, Japan}, author = {Du{\v{s}}ek, Ond{\v{r}}ej and Howcroft, David M. and Rieser, Verena}, booktitle = {Proceedings of the 12th International Conference on Natural Language Generation}, doi = {10.18653/v1/W19-8652}, pages = {421--426}, publisher = {Association for Computational Linguistics}, title = {Semantic Noise Matters for Neural Natural Language Generation}, url = {https://aclanthology.org/W19-8652}, year = {2019} } @article{Mollas2020ETHOSAO, author = {Ioannis Mollas and Zoe Chrysopoulou and Stamatis Karlos and Grigorios Tsoumakas}, journal = {ArXiv preprint}, title = {ETHOS: an Online Hate Speech Detection Dataset}, url = {https://arxiv.org/abs/2006.08328}, volume = {abs/2006.08328}, year = {2020} } @article{financial-phrasebank, abstract = {The use of robo-readers to analyze news texts is an emerging technology trend in computational finance. Recent research has developed sophisticated financial polarity lexicons for investigating how financial sentiments relate to future company performance. However, based on experience from fields that commonly analyze sentiment, it is well known that the overall semantic orientation of a sentence may differ from that of individual words. This article investigates how semantic orientations can be better detected in financial and economic news by accommodating the overall phrase-structure information and domain-specific use of language. Our three main contributions are the following: a a human-annotated finance phrase bank that can be used for training and evaluating alternative models; b a technique to enhance financial lexicons with attributes that help to identify expected direction of events that affect sentiment; and c a linearized phrase-structure model for detecting contextual semantic orientations in economic texts. The relevance of the newly added lexicon features and the benefit of using the proposed learning algorithm are demonstrated in a comparative study against general sentiment models as well as the popular word frequency models used in recent financial studies. The proposed framework is parsimonious and avoids the explosion in feature space caused by the use of conventional n-gram features.}, address = {USA}, author = {Malo, Pekka and Sinha, Ankur and Korhonen, Pekka and Wallenius, Jyrki and Takala, Pyry}, doi = {10.1002/asi.23062}, issn = {2330-1635}, issue_date = {April 2014}, journal = {J. Assoc. Inf. Sci. Technol.}, keywords = {automatic classification, linguistic analysis, economics}, number = {4}, numpages = {15}, pages = {782–796}, publisher = {John Wiley & Sons, Inc.}, title = {Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts}, url = {https://doi.org/10.1002/asi.23062}, volume = {65}, year = {2014} } @article{warstadt-etal-2019-neural, author = {Warstadt, Alex and Singh, Amanpreet and Bowman, Samuel R.}, doi = {10.1162/tacl_a_00290}, journal = {Transactions of the Association for Computational Linguistics}, pages = {625--641}, title = {Neural Network Acceptability Judgments}, url = {https://aclanthology.org/Q19-1040}, volume = {7}, year = {2019} } @inproceedings{dagan2005pascal, author = {Dagan, Ido and Glickman, Oren and Magnini, Bernardo}, booktitle = {Machine Learning Challenges Workshop}, organization = {Springer}, pages = {177--190}, title = {The PASCAL recognising textual entailment challenge}, year = {2005} } @inproceedings{bar2006second, author = {Bar-Haim, Roy and Dagan, Ido and Dolan, Bill and Ferro, Lisa and Giampiccolo, Danilo and Magnini, Bernardo and Szpektor, Idan}, booktitle = {Proceedings of the second PASCAL challenges workshop on recognising textual entailment}, number = {1}, organization = {Venice}, pages = {6--4}, title = {The second pascal recognising textual entailment challenge}, volume = {6}, year = {2006} } @inproceedings{giampiccolo2007third, address = {Prague}, author = {Giampiccolo, Danilo and Magnini, Bernardo and Dagan, Ido and Dolan, Bill}, booktitle = {Proceedings of the {ACL}-{PASCAL} Workshop on Textual Entailment and Paraphrasing}, pages = {1--9}, publisher = {Association for Computational Linguistics}, title = {The Third {PASCAL} Recognizing Textual Entailment Challenge}, url = {https://aclanthology.org/W07-1401}, year = {2007} } @inproceedings{bentivogli2009fifth, author = {Bentivogli, Luisa and Clark, Peter and Dagan, Ido and Giampiccolo, Danilo}, booktitle = {TAC}, title = {The Fifth PASCAL Recognizing Textual Entailment Challenge.}, year = {2009} } @inproceedings{levesque2012winograd, abstract = {In this paper, we present an alternative to the Turing Test that has some conceptual and practical advantages. A Wino-grad schema is a pair of sentences that differ only in one or two words and that contain a referential ambiguity that is resolved in opposite directions in the two sentences. We have compiled a collection of Winograd schemas, designed so that the correct answer is obvious to the human reader, but cannot easily be found using selectional restrictions or statistical techniques over text corpora. A contestant in the Winograd Schema Challenge is presented with a collection of one sentence from each pair, and required to achieve human-level accuracy in choosing the correct disambiguation.}, author = {Levesque, Hector J. and Davis, Ernest and Morgenstern, Leora}, booktitle = {Proceedings of the Thirteenth International Conference on Principles of Knowledge Representation and Reasoning}, isbn = {9781577355601}, location = {Rome, Italy}, numpages = {10}, pages = {552–561}, publisher = {AAAI Press}, series = {KR'12}, title = {The Winograd Schema Challenge}, year = {2012} } @inproceedings{gibert2018hate, address = {Brussels, Belgium}, author = {de Gibert, Ona and Perez, Naiara and Garc{\'\i}a-Pablos, Aitor and Cuadros, Montse}, booktitle = {Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)}, doi = {10.18653/v1/W18-5102}, pages = {11--20}, publisher = {Association for Computational Linguistics}, title = {Hate Speech Dataset from a White Supremacy Forum}, url = {https://aclanthology.org/W18-5102}, year = {2018} } @inproceedings{hateoffensive, author = {Davidson, Thomas and Warmsley, Dana and Macy, Michael and Weber, Ingmar}, booktitle = {Proceedings of the 11th International AAAI Conference on Web and Social Media}, location = {Montreal, Canada}, pages = {512-515}, series = {ICWSM '17}, title = {Automated Hate Speech Detection and the Problem of Offensive Language}, year = {2017} } @article{mathew2020hatexplain, author = {Mathew, Binny and Saha, Punyajoy and Yimam, Seid Muhie and Biemann, Chris and Goyal, Pawan and Mukherjee, Animesh}, journal = {ArXiv preprint}, title = {HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection}, url = {https://arxiv.org/abs/2012.10289}, volume = {abs/2012.10289}, year = {2020} } @inproceedings{kotonya-toni-2020-explainable-automated, address = {Online}, author = {Kotonya, Neema and Toni, Francesca}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.623}, pages = {7740--7754}, publisher = {Association for Computational Linguistics}, title = {Explainable Automated Fact-Checking for Public Health Claims}, url = {https://aclanthology.org/2020.emnlp-main.623}, year = {2020} } @inproceedings{dinan2018wizard, author = {Emily Dinan and Stephen Roller and Kurt Shuster and Angela Fan and Michael Auli and Jason Weston}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/DinanRSFAW19.bib}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, timestamp = {Thu, 30 Jul 2020 01:00:00 +0200}, title = {Wizard of Wikipedia: Knowledge-Powered Conversational Agents}, url = {https://openreview.net/forum?id=r1l73iRqKm}, year = {2019} } @inproceedings{petroni2020how, author = {Fabio Petroni and Patrick Lewis and Aleksandra Piktus and Tim Rockt{\""a}schel and Yuxiang Wu and Alexander H. Miller and Sebastian Riedel}, booktitle = {Automated Knowledge Base Construction}, title = {How Context Affects Language Models' Factual Predictions}, url = {https://openreview.net/forum?id=025X0zPfn}, year = {2020} } @inproceedings{petroni-etal-2019-language, address = {Hong Kong, China}, author = {Petroni, Fabio and Rockt{\""a}schel, Tim and Riedel, Sebastian and Lewis, Patrick and Bakhtin, Anton and Wu, Yuxiang and Miller, Alexander}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1250}, pages = {2463--2473}, publisher = {Association for Computational Linguistics}, title = {Language Models as Knowledge Bases?}, url = {https://aclanthology.org/D19-1250}, year = {2019} } @inproceedings{manotas-etal-2020-limit, address = {Online}, author = {Manotas, Irene and Vo, Ngoc Phuoc An and Sheinin, Vadim}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.88}, pages = {991--1000}, publisher = {Association for Computational Linguistics}, title = {{L}i{M}i{T}: The Literal Motion in Text Dataset}, url = {https://aclanthology.org/2020.findings-emnlp.88}, year = {2020} } @inproceedings{zhou-etal-2019-going, address = {Hong Kong, China}, author = {Zhou, Ben and Khashabi, Daniel and Ning, Qiang and Roth, Dan}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1332}, pages = {3363--3369}, publisher = {Association for Computational Linguistics}, title = {{``}Going on a vacation{''} takes longer than {``}Going for a walk{''}: A Study of Temporal Commonsense Understanding}, url = {https://aclanthology.org/D19-1332}, year = {2019} } @inproceedings{medical-qqp, author = {Clara H. McCreery and Namit Katariya and Anitha Kannan and Manish Chablani and Xavier Amatriain}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/kdd/McCreeryKKCA20.bib}, booktitle = {{KDD} '20: The 26th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020}, editor = {Rajesh Gupta and Yan Liu and Jiliang Tang and B. Aditya Prakash}, pages = {3458--3465}, publisher = {{ACM}}, timestamp = {Mon, 24 Aug 2020 01:00:00 +0200}, title = {Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to {COVID-19} FAQs}, url = {https://dl.acm.org/doi/10.1145/3394486.3412861}, year = {2020} } @inproceedings{chen-etal-2020-mocha, address = {Online}, author = {Chen, Anthony and Stanovsky, Gabriel and Singh, Sameer and Gardner, Matt}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.528}, pages = {6521--6532}, publisher = {Association for Computational Linguistics}, title = {{MOCHA}: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics}, url = {https://aclanthology.org/2020.emnlp-main.528}, year = {2020} } @inproceedings{lin-etal-2020-birds, address = {Online}, author = {Lin, Bill Yuchen and Lee, Seyeon and Khanna, Rahul and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.557}, pages = {6862--6868}, publisher = {Association for Computational Linguistics}, title = {{B}irds have four legs?! {N}umer{S}ense: {P}robing {N}umerical {C}ommonsense {K}nowledge of {P}re-{T}rained {L}anguage {M}odels}, url = {https://aclanthology.org/2020.emnlp-main.557}, year = {2020} } @inproceedings{Bisk2020, author = {Yonatan Bisk and Rowan Zellers and Ronan LeBras and Jianfeng Gao and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/BiskZLGC20.bib}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {7432--7439}, publisher = {{AAAI} Press}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, title = {{PIQA:} Reasoning about Physical Commonsense in Natural Language}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6239}, year = {2020} } @inproceedings{sheng-uthus-2020-investigating, address = {Barcelona, Spain (Online)}, author = {Sheng, Emily and Uthus, David}, booktitle = {Proceedings of the Second Workshop on Gender Bias in Natural Language Processing}, pages = {93--106}, publisher = {Association for Computational Linguistics}, title = {Investigating Societal Biases in a Poetry Composition System}, url = {https://aclanthology.org/2020.gebnlp-1.9}, year = {2020} } @inproceedings{boratko-etal-2020-protoqa, address = {Online}, author = {Boratko, Michael and Li, Xiang and O{'}Gorman, Tim and Das, Rajarshi and Le, Dan and McCallum, Andrew}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.85}, pages = {1122--1136}, publisher = {Association for Computational Linguistics}, title = {{P}roto{QA}: A Question Answering Dataset for Prototypical Common-Sense Reasoning}, url = {https://aclanthology.org/2020.emnlp-main.85}, year = {2020} } @inproceedings{tafjord-etal-2019-quartz, address = {Hong Kong, China}, author = {Tafjord, Oyvind and Gardner, Matt and Lin, Kevin and Clark, Peter}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1608}, pages = {5941--5946}, publisher = {Association for Computational Linguistics}, title = {{Q}ua{RT}z: An Open-Domain Dataset of Qualitative Relationship Questions}, url = {https://aclanthology.org/D19-1608}, year = {2019} } @inproceedings{dasigi-etal-2019-quoref, address = {Hong Kong, China}, author = {Dasigi, Pradeep and Liu, Nelson F. and Marasovi{\'c}, Ana and Smith, Noah A. and Gardner, Matt}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1606}, pages = {5925--5932}, publisher = {Association for Computational Linguistics}, title = {{Q}uoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning}, url = {https://aclanthology.org/D19-1606}, year = {2019} } @inproceedings{lin-etal-2019-reasoning, address = {Hong Kong, China}, author = {Lin, Kevin and Tafjord, Oyvind and Clark, Peter and Gardner, Matt}, booktitle = {Proceedings of the 2nd Workshop on Machine Reading for Question Answering}, doi = {10.18653/v1/D19-5808}, pages = {58--62}, publisher = {Association for Computational Linguistics}, title = {Reasoning Over Paragraph Effects in Situations}, url = {https://aclanthology.org/D19-5808}, year = {2019} } @inproceedings{gliwa-etal-2019-samsum, address = {Hong Kong, China}, author = {Gliwa, Bogdan and Mochol, Iwona and Biesek, Maciej and Wawer, Aleksander}, booktitle = {Proceedings of the 2nd Workshop on New Frontiers in Summarization}, doi = {10.18653/v1/D19-5409}, pages = {70--79}, publisher = {Association for Computational Linguistics}, title = {{SAMS}um Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization}, url = {https://aclanthology.org/D19-5409}, year = {2019} } @inproceedings{scitail, author = {Tushar Khot and Ashish Sabharwal and Peter Clark}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/aaai/KhotSC18.bib}, booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018}, editor = {Sheila A. McIlraith and Kilian Q. Weinberger}, pages = {5189--5197}, publisher = {{AAAI} Press}, timestamp = {Mon, 22 Oct 2018 01:00:00 +0200}, title = {SciTaiL: {A} Textual Entailment Dataset from Science Question Answering}, url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17368}, year = {2018} } @inproceedings{sms_spam, abstract = {The growth of mobile phone users has lead to a dramatic increasing of SMS spam messages. In practice, fighting mobile phone spam is difficult by several factors, including the lower rate of SMS that has allowed many users and service providers to ignore the issue, and the limited availability of mobile phone spam-filtering software. On the other hand, in academic settings, a major handicap is the scarcity of public SMS spam datasets, that are sorely needed for validation and comparison of different classifiers. Moreover, as SMS messages are fairly short, content-based spam filters may have their performance degraded. In this paper, we offer a new real, public and non-encoded SMS spam collection that is the largest one as far as we know. Moreover, we compare the performance achieved by several established machine learning methods. The results indicate that Support Vector Machine outperforms other evaluated classifiers and, hence, it can be used as a good baseline for further comparison.}, address = {New York, NY, USA}, author = {Almeida, Tiago A. and Hidalgo, Jos\'{e} Mar\'{\i}a G. and Yamakami, Akebo}, booktitle = {Proceedings of the 11th ACM Symposium on Document Engineering}, doi = {10.1145/2034691.2034742}, isbn = {9781450308632}, keywords = {mobile spam, spam filtering, classification}, location = {Mountain View, California, USA}, numpages = {4}, pages = {259–262}, publisher = {Association for Computing Machinery}, series = {DocEng '11}, title = {Contributions to the Study of SMS Spam Filtering: New Collection and Results}, url = {https://doi.org/10.1145/2034691.2034742}, year = {2011} } @article{Zhang2018ReCoRDBT, author = {Sheng Zhang and X. Liu and J. Liu and Jianfeng Gao and Kevin Duh and Benjamin Van Durme}, journal = {ArXiv preprint}, title = {ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension}, url = {https://arxiv.org/abs/1810.12885}, volume = {abs/1810.12885}, year = {2018} } @inproceedings{Chen2020TabFact, author = {Wenhu Chen and Hongmin Wang and Jianshu Chen and Yunkai Zhang and Hong Wang and Shiyang Li and Xiyou Zhou and William Yang Wang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ChenWCZWLZW20.bib}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, timestamp = {Thu, 07 May 2020 01:00:00 +0200}, title = {TabFact: {A} Large-scale Dataset for Table-based Fact Verification}, url = {https://openreview.net/forum?id=rkeJRhNYDH}, year = {2020} } @inproceedings{barbieri-etal-2020-tweeteval, address = {Online}, author = {Barbieri, Francesco and Camacho-Collados, Jose and Espinosa Anke, Luis and Neves, Leonardo}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.148}, pages = {1644--1650}, publisher = {Association for Computational Linguistics}, title = {{T}weet{E}val: Unified Benchmark and Comparative Evaluation for Tweet Classification}, url = {https://aclanthology.org/2020.findings-emnlp.148}, year = {2020} } @inproceedings{jiang-etal-2020-neural, address = {Online}, author = {Jiang, Chao and Maddela, Mounica and Lan, Wuwei and Zhong, Yang and Xu, Wei}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.709}, pages = {7943--7960}, publisher = {Association for Computational Linguistics}, title = {Neural {CRF} Model for Sentence Alignment in Text Simplification}, url = {https://aclanthology.org/2020.acl-main.709}, year = {2020} } @article{zhongSeq2SQL2017, author = {Victor Zhong an}, journal = {ArXiv preprint}, title = {Seq2SQL: Generating Structured Queries from Natural Language usin}, url = {https://arxiv.org/abs/1709.00103}, volume = {abs/1709.00103}, year = {2017} } @inproceedings{tandon-etal-2019-wiqa, address = {Hong Kong, China}, author = {Tandon, Niket and Dalvi, Bhavana and Sakaguchi, Keisuke and Clark, Peter and Bosselut, Antoine}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)}, doi = {10.18653/v1/D19-1629}, pages = {6076--6085}, publisher = {Association for Computational Linguistics}, title = {{WIQA}: A dataset for {``}What if...{''} reasoning over procedural text}, url = {https://aclanthology.org/D19-1629}, year = {2019} } @inproceedings{zhang2015character, author = {Xiang Zhang and Junbo Jake Zhao and Yann LeCun}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ZhangZL15.bib}, booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada}, editor = {Corinna Cortes and Neil D. Lawrence and Daniel D. Lee and Masashi Sugiyama and Roman Garnett}, pages = {649--657}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Character-level Convolutional Networks for Text Classification}, url = {https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html}, year = {2015} } @inproceedings{sileo-etal-2019-mining, address = {Minneapolis, Minnesota}, author = {Sileo, Damien and Van De Cruys, Tim and Pradel, Camille and Muller, Philippe}, booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, doi = {10.18653/v1/N19-1351}, pages = {3477--3486}, publisher = {Association for Computational Linguistics}, title = {Mining Discourse Markers for Unsupervised Sentence Representation Learning}, url = {https://aclanthology.org/N19-1351}, year = {2019} } @inproceedings{schwarz2018progress, author = {Jonathan Schwarz and Wojciech Czarnecki and Jelena Luketina and Agnieszka Grabska{-}Barwinska and Yee Whye Teh and Razvan Pascanu and Raia Hadsell}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/icml/Schwarz0LGTPH18.bib}, booktitle = {Proceedings of the 35th International Conference on Machine Learning, {ICML} 2018, Stockholmsm{\""{a}}ssan, Stockholm, Sweden, July 10-15, 2018}, editor = {Jennifer G. Dy and Andreas Krause}, pages = {4535--4544}, publisher = {{PMLR}}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 03 Apr 2019 01:00:00 +0200}, title = {Progress {\&} Compress: {A} scalable framework for continual learning}, url = {http://proceedings.mlr.press/v80/schwarz18a.html}, volume = {80}, year = {2018} } @inproceedings{brown2020language, author = {Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert{-}Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/BrownMRSKDNSSAA20.bib}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, title = {Language Models are Few-Shot Learners}, url = {https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html}, year = {2020} } @inproceedings{verga2020facts, author = {Verga, Pat and Sun, Haitian and Soares, Livio Baldini and Cohen, William W}, booktitle = {NAACL}, title = {Facts as experts: Adaptable and interpretable neural memory over symbolic knowledge}, year = {2021} } @inproceedings{fevry2020entities, address = {Online}, author = {F{\'e}vry, Thibault and Baldini Soares, Livio and FitzGerald, Nicholas and Choi, Eunsol and Kwiatkowski, Tom}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.400}, pages = {4937--4951}, publisher = {Association for Computational Linguistics}, title = {Entities as Experts: Sparse Memory Access with Entity Supervision}, url = {https://aclanthology.org/2020.emnlp-main.400}, year = {2020} } @inproceedings{tenney2019bert, address = {Florence, Italy}, author = {Tenney, Ian and Das, Dipanjan and Pavlick, Ellie}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1452}, pages = {4593--4601}, publisher = {Association for Computational Linguistics}, title = {{BERT} Rediscovers the Classical {NLP} Pipeline}, url = {https://aclanthology.org/P19-1452}, year = {2019} } @article{zhu2020modifying, author = {Zhu, Chen and Rawat, Ankit Singh and Zaheer, Manzil and Bhojanapalli, Srinadh and Li, Daliang and Yu, Felix and Kumar, Sanjiv}, journal = {ArXiv preprint}, title = {Modifying Memories in Transformer Models}, url = {https://arxiv.org/abs/2012.00363}, volume = {abs/2012.00363}, year = {2020} } @inproceedings{joshi2017triviaqa, address = {Vancouver, Canada}, author = {Joshi, Mandar and Choi, Eunsol and Weld, Daniel and Zettlemoyer, Luke}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/P17-1147}, pages = {1601--1611}, publisher = {Association for Computational Linguistics}, title = {{T}rivia{QA}: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension}, url = {https://aclanthology.org/P17-1147}, year = {2017} } @inproceedings{chen2020recall, address = {Online}, author = {Chen, Sanyuan and Hou, Yutai and Cui, Yiming and Che, Wanxiang and Liu, Ting and Yu, Xiangzhan}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.634}, pages = {7870--7881}, publisher = {Association for Computational Linguistics}, title = {Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting}, url = {https://aclanthology.org/2020.emnlp-main.634}, year = {2020} } @inproceedings{wang2020k, address = {Online}, author = {Wang, Ruize and Tang, Duyu and Duan, Nan and Wei, Zhongyu and Huang, Xuanjing and Ji, Jianshu and Cao, Guihong and Jiang, Daxin and Zhou, Ming}, booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021}, doi = {10.18653/v1/2021.findings-acl.121}, pages = {1405--1418}, publisher = {Association for Computational Linguistics}, title = {{K-Adapter}: {I}nfusing {K}nowledge into {P}re-{T}rained {M}odels with {A}dapters}, url = {https://aclanthology.org/2021.findings-acl.121}, year = {2021} } @article{patterson2021carbon, author = {Patterson, David and Gonzalez, Joseph and Le, Quoc and Liang, Chen and Munguia, Lluis-Miquel and Rothchild, Daniel and So, David and Texier, Maud and Dean, Jeff}, journal = {ArXiv preprint}, title = {Carbon emissions and large neural network training}, url = {https://arxiv.org/abs/2104.10350}, volume = {abs/2104.10350}, year = {2021} } @inproceedings{hamborg2017news, author = {Hamborg, Felix and Meuschke, Norman and Breitinger, Corinna and Gipp, Bela}, booktitle = {15th International Symposium of Information Science (ISI 2017)}, pages = {218--223}, title = {news-please: A generic news crawler and extractor}, year = {2017} } @inproceedings{zellers2019defending, author = {Rowan Zellers and Ari Holtzman and Hannah Rashkin and Yonatan Bisk and Ali Farhadi and Franziska Roesner and Yejin Choi}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/ZellersHRBFRC19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {9051--9062}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Defending Against Neural Fake News}, url = {https://proceedings.neurips.cc/paper/2019/hash/3e9f0fc9b2f89e043bc6233994dfcf76-Abstract.html}, year = {2019} } @article{liu2019roberta, author = {Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, Veselin}, journal = {ArXiv preprint}, title = {Roberta: A robustly optimized bert pretraining approach}, url = {https://arxiv.org/abs/1907.11692}, volume = {abs/1907.11692}, year = {2019} } @inproceedings{vig2020causal, author = {Vig, Jesse and Gehrmann, Sebastian and Belinkov, Yonatan and Qian, Sharon and Nevo, Daniel and Sakenis, Simas and Huang, Jason and Singer, Yaron and Shieber, Stuart}, booktitle = {NeurIPS}, title = {Causal mediation analysis for interpreting neural nlp: The case of gender bias}, year = {2020} } @inproceedings{de2021editing, address = {Online and Punta Cana, Dominican Republic}, author = {De Cao, Nicola and Aziz, Wilker and Titov, Ivan}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.522}, pages = {6491--6506}, publisher = {Association for Computational Linguistics}, title = {Editing Factual Knowledge in Language Models}, url = {https://aclanthology.org/2021.emnlp-main.522}, year = {2021} } @article{fedus2021switch, author = {Fedus, William and Zoph, Barret and Shazeer, Noam}, journal = {ArXiv preprint}, title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity}, url = {https://arxiv.org/abs/2101.03961}, volume = {abs/2101.03961}, year = {2021} } @inproceedings{lepikhin2020gshard, author = {Dmitry Lepikhin and HyoukJoong Lee and Yuanzhong Xu and Dehao Chen and Orhan Firat and Yanping Huang and Maxim Krikun and Noam Shazeer and Zhifeng Chen}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/LepikhinLXCFHKS21.bib}, booktitle = {9th International Conference on Learning Representations, {ICLR} 2021, Virtual Event, Austria, May 3-7, 2021}, publisher = {OpenReview.net}, timestamp = {Wed, 23 Jun 2021 01:00:00 +0200}, title = {GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding}, url = {https://openreview.net/forum?id=qrwe7XHTmYb}, year = {2021} } @inproceedings{he2021analyzing, address = {Online}, author = {He, Tianxing and Liu, Jun and Cho, Kyunghyun and Ott, Myle and Liu, Bing and Glass, James and Peng, Fuchun}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, pages = {1121--1133}, publisher = {Association for Computational Linguistics}, title = {Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models}, url = {https://aclanthology.org/2021.eacl-main.95}, year = {2021} } @inproceedings{d2019episodic, author = {Cyprien de Masson d'Autume and Sebastian Ruder and Lingpeng Kong and Dani Yogatama}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/nips/dAutumeRKY19.bib}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, pages = {13122--13131}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, title = {Episodic Memory in Lifelong Language Learning}, url = {https://proceedings.neurips.cc/paper/2019/hash/f8d2e80c1458ea2501f98a2cafadb397-Abstract.html}, year = {2019} } @inproceedings{poerner2019bert, address = {Online}, author = {Poerner, Nina and Waltinger, Ulli and Sch{\""u}tze, Hinrich}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020}, doi = {10.18653/v1/2020.findings-emnlp.71}, pages = {803--818}, publisher = {Association for Computational Linguistics}, title = {{E}-{BERT}: Efficient-Yet-Effective Entity Embeddings for {BERT}}, url = {https://aclanthology.org/2020.findings-emnlp.71}, year = {2020} } @inproceedings{elsahar2019t, address = {Miyazaki, Japan}, author = {Elsahar, Hady and Vougiouklis, Pavlos and Remaci, Arslen and Gravier, Christophe and Hare, Jonathon and Laforest, Frederique and Simperl, Elena}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {European Language Resources Association (ELRA)}, title = {{T}-{RE}x: A Large Scale Alignment of Natural Language with Knowledge Base Triples}, url = {https://aclanthology.org/L18-1544}, year = {2018} } @inproceedings{wolf-etal-2020-transformers, address = {Online}, author = {Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien and Delangue, Clement and Moi, Anthony and Cistac, Pierric and Rault, Tim and Louf, Remi and Funtowicz, Morgan and Davison, Joe and Shleifer, Sam and von Platen, Patrick and Ma, Clara and Jernite, Yacine and Plu, Julien and Xu, Canwen and Le Scao, Teven and Gugger, Sylvain and Drame, Mariama and Lhoest, Quentin and Rush, Alexander}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations}, doi = {10.18653/v1/2020.emnlp-demos.6}, pages = {38--45}, publisher = {Association for Computational Linguistics}, title = {Transformers: State-of-the-Art Natural Language Processing}, url = {https://aclanthology.org/2020.emnlp-demos.6}, year = {2020} } @inproceedings{zhang2021neural, address = {Online}, author = {Zhang, Zhiyuan and Ren, Xuancheng and Su, Qi and Sun, Xu and He, Bin}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, doi = {10.18653/v1/2021.naacl-main.430}, pages = {5453--5466}, publisher = {Association for Computational Linguistics}, title = {Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects}, url = {https://aclanthology.org/2021.naacl-main.430}, year = {2021} } @inproceedings{thorne2018fever, address = {New Orleans, Louisiana}, author = {Thorne, James and Vlachos, Andreas and Christodoulopoulos, Christos and Mittal, Arpit}, booktitle = {Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}, doi = {10.18653/v1/N18-1074}, pages = {809--819}, publisher = {Association for Computational Linguistics}, title = {{FEVER}: a Large-scale Dataset for Fact Extraction and {VER}ification}, url = {https://aclanthology.org/N18-1074}, year = {2018} } @article{Yao2021RefiningNN, author = {Huihan Yao and Ying Chen and Qinyuan Ye and Xisen Jin and Xiang Ren}, journal = {ArXiv preprint}, title = {Refining Neural Networks with Compositional Explanations}, url = {https://arxiv.org/abs/2103.10415}, volume = {abs/2103.10415}, year = {2021} } @inproceedings{fan2019eli5, address = {Florence, Italy}, author = {Fan, Angela and Jernite, Yacine and Perez, Ethan and Grangier, David and Weston, Jason and Auli, Michael}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/P19-1346}, pages = {3558--3567}, publisher = {Association for Computational Linguistics}, title = {{ELI}5: Long Form Question Answering}, url = {https://aclanthology.org/P19-1346}, year = {2019} } @inproceedings{hoffart2011robust, address = {Edinburgh, Scotland, UK.}, author = {Hoffart, Johannes and Yosef, Mohamed Amir and Bordino, Ilaria and F{\""u}rstenau, Hagen and Pinkal, Manfred and Spaniol, Marc and Taneva, Bilyana and Thater, Stefan and Weikum, Gerhard}, booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing}, pages = {782--792}, publisher = {Association for Computational Linguistics}, title = {Robust Disambiguation of Named Entities in Text}, url = {https://aclanthology.org/D11-1072}, year = {2011} } @article{guo2018robust, author = {Guo, Zhaochen and Barbosa, Denilson}, journal = {Semantic Web}, number = {4}, pages = {459--479}, publisher = {IOS Press}, title = {Robust named entity disambiguation with random walks}, volume = {9}, year = {2018} } @inproceedings{levy2017zero, address = {Vancouver, Canada}, author = {Levy, Omer and Seo, Minjoon and Choi, Eunsol and Zettlemoyer, Luke}, booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)}, doi = {10.18653/v1/K17-1034}, pages = {333--342}, publisher = {Association for Computational Linguistics}, title = {Zero-Shot Relation Extraction via Reading Comprehension}, url = {https://aclanthology.org/K17-1034}, year = {2017} } @article{hu2021lora, author = {Hu, Edward J and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu}, journal = {ArXiv preprint}, title = {LoRA: Low-Rank Adaptation of Large Language Models}, url = {https://arxiv.org/abs/2106.09685}, volume = {abs/2106.09685}, year = {2021} } @inproceedings{lewis2020question, address = {Online}, author = {Lewis, Patrick and Stenetorp, Pontus and Riedel, Sebastian}, booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume}, pages = {1000--1008}, publisher = {Association for Computational Linguistics}, title = {Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets}, url = {https://aclanthology.org/2021.eacl-main.86}, year = {2021} } @article{lewis2021paq, address = {Cambridge, MA}, author = {Lewis, Patrick and Wu, Yuxiang and Liu, Linqing and Minervini, Pasquale and K{\""u}ttler, Heinrich and Piktus, Aleksandra and Stenetorp, Pontus and Riedel, Sebastian}, doi = {10.1162/tacl_a_00415}, journal = {Transactions of the Association for Computational Linguistics}, pages = {1098--1115}, publisher = {MIT Press}, title = {{PAQ}: 65 Million Probably-Asked Questions and What You Can Do With Them}, url = {https://aclanthology.org/2021.tacl-1.65}, volume = {9}, year = {2021} } @article{choi2021decontextualization, address = {Cambridge, MA}, author = {Choi, Eunsol and Palomaki, Jennimaria and Lamm, Matthew and Kwiatkowski, Tom and Das, Dipanjan and Collins, Michael}, doi = {10.1162/tacl_a_00377}, journal = {Transactions of the Association for Computational Linguistics}, pages = {447--461}, publisher = {MIT Press}, title = {Decontextualization: Making Sentences Stand-Alone}, url = {https://aclanthology.org/2021.tacl-1.27}, volume = {9}, year = {2021} } @inproceedings{sang2003introduction, author = {Tjong Kim Sang, Erik F.}, booktitle = {{COLING}-02: The 6th Conference on Natural Language Learning 2002 ({C}o{NLL}-2002)}, title = {Introduction to the {C}o{NLL}-2002 Shared Task: Language-Independent Named Entity Recognition}, url = {https://aclanthology.org/W02-2024}, year = {2002} } @inproceedings{xu2021beyond, address = {Dublin, Ireland}, author = {Xu, Jing and Szlam, Arthur and Weston, Jason}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.356}, pages = {5180--5197}, publisher = {Association for Computational Linguistics}, title = {Beyond Goldfish Memory: Long-Term Open-Domain Conversation}, url = {https://aclanthology.org/2022.acl-long.356}, year = {2022} } @inproceedings{komeili2021internet, address = {Dublin, Ireland}, author = {Komeili, Mojtaba and Shuster, Kurt and Weston, Jason}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.579}, pages = {8460--8478}, publisher = {Association for Computational Linguistics}, title = {{I}nternet-Augmented Dialogue Generation}, url = {https://aclanthology.org/2022.acl-long.579}, year = {2022} } @inproceedings{bang2021rainbow, author = {Bang, Jihwan and Kim, Heesu and Yoo, YoungJoon and Ha, Jung-Woo and Choi, Jonghyun}, booktitle = {CVPR}, title = {Rainbow Memory: Continual Learning with a Memory of Diverse Samples}, year = {2021} } @inproceedings{prabhu2020gdumb, author = {Prabhu, Ameya and Torr, Philip HS and Dokania, Puneet K}, booktitle = {ECCV}, title = {Gdumb: A simple approach that questions our progress in continual learning}, year = {2020} } @inproceedings{chuang2020lifelong, address = {Online}, author = {Chuang, Yung-Sung and Su, Shang-Yu and Chen, Yun-Nung}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.233}, pages = {2914--2924}, publisher = {Association for Computational Linguistics}, title = {Lifelong Language Knowledge Distillation}, url = {https://aclanthology.org/2020.emnlp-main.233}, year = {2020} } @inproceedings{TiedemannThottingal:EAMT2020, address = {Lisboa, Portugal}, author = {Tiedemann, J{\""o}rg and Thottingal, Santhosh}, booktitle = {Proceedings of the 22nd Annual Conference of the European Association for Machine Translation}, pages = {479--480}, publisher = {European Association for Machine Translation}, title = {{OPUS}-{MT} {--} Building open translation services for the World}, url = {https://aclanthology.org/2020.eamt-1.61}, year = {2020} } @inproceedings{longpre2021entity, address = {Online and Punta Cana, Dominican Republic}, author = {Longpre, Shayne and Perisetla, Kartik and Chen, Anthony and Ramesh, Nikhil and DuBois, Chris and Singh, Sameer}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.565}, pages = {7052--7063}, publisher = {Association for Computational Linguistics}, title = {Entity-Based Knowledge Conflicts in Question Answering}, url = {https://aclanthology.org/2021.emnlp-main.565}, year = {2021} } @inproceedings{wang2021can, address = {Online}, author = {Wang, Cunxiang and Liu, Pai and Zhang, Yue}, booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, doi = {10.18653/v1/2021.acl-long.251}, pages = {3241--3251}, publisher = {Association for Computational Linguistics}, title = {Can Generative Pre-trained Language Models Serve As Knowledge Bases for Closed-book {QA}?}, url = {https://aclanthology.org/2021.acl-long.251}, year = {2021} } @inproceedings{zhou2020pre, author = {Wangchunshu Zhou and Dong{-}Ho Lee and Ravi Kiran Selvam and Seyeon Lee and Xiang Ren}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/ZhouLSL021.bib}, booktitle = {9th International Conference on Learning Representations, {ICLR} 2021, Virtual Event, Austria, May 3-7, 2021}, publisher = {OpenReview.net}, timestamp = {Wed, 23 Jun 2021 01:00:00 +0200}, title = {Pre-training Text-to-Text Transformers for Concept-centric Common Sense}, url = {https://openreview.net/forum?id=3k20LAiHYL2}, year = {2021} } @article{li2021efficient, author = {Li, Yanyang and Lin, Ye and Xiao, Tong and Zhu, Jingbo}, journal = {ArXiv preprint}, title = {An efficient transformer decoder with compressed sub-layers}, url = {https://arxiv.org/abs/2101.00542}, volume = {abs/2101.00542}, year = {2021} } @inproceedings{lee2021deduplicating, address = {Dublin, Ireland}, author = {Lee, Katherine and Ippolito, Daphne and Nystrom, Andrew and Zhang, Chiyuan and Eck, Douglas and Callison-Burch, Chris and Carlini, Nicholas}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.577}, pages = {8424--8445}, publisher = {Association for Computational Linguistics}, title = {Deduplicating Training Data Makes Language Models Better}, url = {https://aclanthology.org/2022.acl-long.577}, year = {2022} } @inproceedings{autoprompt:emnlp20, address = {Online}, author = {Shin, Taylor and Razeghi, Yasaman and Logan IV, Robert L. and Wallace, Eric and Singh, Sameer}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.346}, pages = {4222--4235}, publisher = {Association for Computational Linguistics}, title = {{A}uto{P}rompt: {E}liciting {K}nowledge from {L}anguage {M}odels with {A}utomatically {G}enerated {P}rompts}, url = {https://aclanthology.org/2020.emnlp-main.346}, year = {2020} } @inproceedings{gururangan2020don, address = {Online}, author = {Gururangan, Suchin and Marasovi{\'c}, Ana and Swayamdipta, Swabha and Lo, Kyle and Beltagy, Iz and Downey, Doug and Smith, Noah A.}, booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, doi = {10.18653/v1/2020.acl-main.740}, pages = {8342--8360}, publisher = {Association for Computational Linguistics}, title = {Don{'}t Stop Pretraining: Adapt Language Models to Domains and Tasks}, url = {https://aclanthology.org/2020.acl-main.740}, year = {2020} } @inproceedings{yoon2017lifelong, author = {Jaehong Yoon and Eunho Yang and Jeongtae Lee and Sung Ju Hwang}, bibsource = {dblp computer science bibliography, https://dblp.org}, biburl = {https://dblp.org/rec/conf/iclr/YoonYLH18.bib}, booktitle = {6th International Conference on Learning Representations, {ICLR} 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings}, publisher = {OpenReview.net}, timestamp = {Thu, 25 Jul 2019 01:00:00 +0200}, title = {Lifelong Learning with Dynamically Expandable Networks}, url = {https://openreview.net/forum?id=Sk7KsfW0-}, year = {2018} } @inproceedings{zhang2021situatedqa, address = {Online and Punta Cana, Dominican Republic}, author = {Zhang, Michael and Choi, Eunsol}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, doi = {10.18653/v1/2021.emnlp-main.586}, pages = {7371--7387}, publisher = {Association for Computational Linguistics}, title = {{S}ituated{QA}: Incorporating Extra-Linguistic Contexts into {QA}}, url = {https://aclanthology.org/2021.emnlp-main.586}, year = {2021} } @article{dhingra2021time, address = {Cambridge, MA}, author = {Dhingra, Bhuwan and Cole, Jeremy R. and Eisenschlos, Julian Martin and Gillick, Daniel and Eisenstein, Jacob and Cohen, William W.}, doi = {10.1162/tacl_a_00459}, journal = {Transactions of the Association for Computational Linguistics}, pages = {257--273}, publisher = {MIT Press}, title = {Time-Aware Language Models as Temporal Knowledge Bases}, url = {https://aclanthology.org/2022.tacl-1.15}, volume = {10}, year = {2022} } @inproceedings{Dai2021KnowledgeNI, address = {Dublin, Ireland}, author = {Dai, Damai and Dong, Li and Hao, Yaru and Sui, Zhifang and Chang, Baobao and Wei, Furu}, booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, doi = {10.18653/v1/2022.acl-long.581}, pages = {8493--8502}, publisher = {Association for Computational Linguistics}, title = {Knowledge Neurons in Pretrained Transformers}, url = {https://aclanthology.org/2022.acl-long.581}, year = {2022} } @article{lazaridou2021pitfalls, author = {Lazaridou, Angeliki and Kuncoro, Adhiguna and Gribovskaya, Elena and Agrawal, Devang and Liska, Adam and Terzi, Tayfun and Gimenez, Mai and d'Autume, Cyprien de Masson and Ruder, Sebastian and Yogatama, Dani and others}, journal = {ArXiv preprint}, title = {Pitfalls of Static Language Modelling}, url = {https://arxiv.org/abs/2102.01951}, volume = {abs/2102.01951}, year = {2021} } @inproceedings{jin2021lifelong, address = {virtual+Dublin}, author = {Jin, Xisen and Zhang, Dejiao and Zhu, Henghui and Xiao, Wei and Li, Shang-Wen and Wei, Xiaokai and Arnold, Andrew and Ren, Xiang}, booktitle = {Proceedings of BigScience Episode {\#}5 -- Workshop on Challenges {\&} Perspectives in Creating Large Language Models}, doi = {10.18653/v1/2022.bigscience-1.1}, pages = {1--16}, publisher = {Association for Computational Linguistics}, title = {Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora}, url = {https://aclanthology.org/2022.bigscience-1.1}, year = {2022} } ",,,2023-05-30 20:13:44.978360 "' @article{lin2020birds, title={Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models}, author={Lin, Bill Yuchen and Lee, Seyeon and Khanna, Rahul and Ren, Xiang}, journal={arXiv preprint arXiv:2005.00683}, year={2020} } ","'@inproceedings{lin2020birds, address = {Online}, author = {Lin, Bill Yuchen and Lee, Seyeon and Khanna, Rahul and Ren, Xiang}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.557}, pages = {6862--6868}, publisher = {Association for Computational Linguistics}, title = {{B}irds have four legs?! {N}umer{S}ense: {P}robing {N}umerical {C}ommonsense {K}nowledge of {P}re-{T}rained {L}anguage {M}odels}, url = {https://aclanthology.org/2020.emnlp-main.557}, year = {2020} } ",,,2023-05-30 20:20:16.444789