|
|
|
--- |
|
tags: |
|
- MRC |
|
- SQuAD 1.1 |
|
- xlm-roberta-large |
|
language: |
|
- multilingual |
|
license: apache-2.0 |
|
--- |
|
|
|
# Model description |
|
|
|
An XLM-RoBERTa reading comprehension model for [SQuAD 1.1](https://aclanthology.org/D16-1264/). |
|
|
|
The model is initialized with [xlm-roberta-large](https://huggingface.co/xlm-roberta-large/) and fine-tuned on the [SQuAD 1.1 train data](https://huggingface.co/datasets/squad). |
|
|
|
## Intended uses & limitations |
|
|
|
You can use the raw model for the reading comprehension task. Biases associated with the pre-existing language model, xlm-roberta-large, that we used may be present in our fine-tuned model, squad-v1-xlm-roberta-large. This model is used for zero-shot decoding of [MLQA](https://huggingface.co/datasets/mlqa) and [XQuAD](https://huggingface.co/datasets/xquad) datasets. |
|
|
|
|
|
## Usage |
|
|
|
You can use this model directly with the [PrimeQA](https://github.com/primeqa/primeqa) pipeline for reading comprehension [squad.ipynb](https://github.com/primeqa/primeqa/blob/main/notebooks/mrc/squad.ipynb). |
|
|
|
```bibtex |
|
@article{2016arXiv160605250R, |
|
author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev}, |
|
Konstantin and {Liang}, Percy}, |
|
title = "{SQuAD: 100,000+ Questions for Machine Comprehension of Text}", |
|
journal = {arXiv e-prints}, |
|
year = 2016, |
|
eid = {arXiv:1606.05250}, |
|
pages = {arXiv:1606.05250}, |
|
archivePrefix = {arXiv}, |
|
eprint = {1606.05250}, |
|
} |
|
``` |
|
```bibtex |
|
@article{lewis2019mlqa, |
|
title={MLQA: Evaluating Cross-lingual Extractive Question Answering}, |
|
author={Lewis, Patrick and Oguz, Barlas and Rinott, Ruty and Riedel, Sebastian and Schwenk, Holger}, |
|
journal={arXiv preprint arXiv:1910.07475}, |
|
year={2019} |
|
} |
|
``` |
|
|
|
```bibtex |
|
@article{Artetxe:etal:2019, |
|
author = {Mikel Artetxe and Sebastian Ruder and Dani Yogatama}, |
|
title = {On the cross-lingual transferability of monolingual representations}, |
|
journal = {CoRR}, |
|
volume = {abs/1910.11856}, |
|
year = {2019}, |
|
archivePrefix = {arXiv}, |
|
eprint = {1910.11856} |
|
} |
|
``` |
|
|
|
```bibtex |
|
@article{DBLP:journals/corr/abs-1911-02116, |
|
author = {Alexis Conneau and |
|
Kartikay Khandelwal and |
|
Naman Goyal and |
|
Vishrav Chaudhary and |
|
Guillaume Wenzek and |
|
Francisco Guzm{\'{a}}n and |
|
Edouard Grave and |
|
Myle Ott and |
|
Luke Zettlemoyer and |
|
Veselin Stoyanov}, |
|
title = {Unsupervised Cross-lingual Representation Learning at Scale}, |
|
journal = {CoRR}, |
|
volume = {abs/1911.02116}, |
|
year = {2019}, |
|
url = {http://arxiv.org/abs/1911.02116}, |
|
eprinttype = {arXiv}, |
|
eprint = {1911.02116}, |
|
timestamp = {Mon, 11 Nov 2019 18:38:09 +0100}, |
|
biburl = {https://dblp.org/rec/journals/corr/abs-1911-02116.bib}, |
|
bibsource = {dblp computer science bibliography, https://dblp.org} |
|
} |
|
``` |