Added citation, github repo and paper link to model card.

a83e7b0 about 1 year ago

No virus

6.84 kB

	---
	tags:
	- information retrieval
	- reranking
	license: apache-2.0
	---

	# Model Card for NQ Question Encoder in Re2G

	# Model Details

	> The approach of RAG, Multi-DPR, and KGI is to train a neural IR (Information Retrieval) component and further train it end-to-end through its impact in generating the correct output.

	<img src="https://github.com/IBM/kgi-slot-filling/raw/re2g/model_cards/Re2G_Arch2.png" width="100%">

	## Training, Evaluation and Inference
	The code for training, evaluation and inference is in our github in the [re2g branch](https://github.com/IBM/kgi-slot-filling/tree/re2g).

	## Usage

	The best way to use the model is by adapting the [dpr_apply.py](https://github.com/IBM/kgi-slot-filling/blob/re2g/dpr/dpr_apply.py)

	## Citation
	```
	@inproceedings{glass-etal-2022-re2g,
	title = "{R}e2{G}: Retrieve, Rerank, Generate",
	author = "Glass, Michael and
	Rossiello, Gaetano and
	Chowdhury, Md Faisal Mahbub and
	Naik, Ankita and
	Cai, Pengshan and
	Gliozzo, Alfio",
	booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
	month = jul,
	year = "2022",
	address = "Seattle, United States",
	publisher = "Association for Computational Linguistics",
	url = "https://aclanthology.org/2022.naacl-main.194",
	doi = "10.18653/v1/2022.naacl-main.194",
	pages = "2701--2715",
	abstract = "As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-parametric memory allows models to grow dramatically with a sub-linear increase in computational cost and GPU memory requirements. Recent models such as RAG and REALM have introduced retrieval into conditional generation. These models incorporate neural initial retrieval from a corpus of passages. We build on this line of research, proposing Re2G, which combines both neural initial retrieval and reranking into a BART-based sequence-to-sequence generation. Our reranking approach also permits merging retrieval results from sources with incomparable scores, enabling an ensemble of BM25 and neural initial retrieval. To train our system end-to-end, we introduce a novel variation of knowledge distillation to train the initial retrieval, reranker and generation using only ground truth on the target sequence output. We find large gains in four diverse tasks: zero-shot slot filling, question answering, fact checking and dialog, with relative gains of 9{\%} to 34{\%} over the previous state-of-the-art on the KILT leaderboard. We make our code available as open source.",
	}
	```

	## Model Description
	The model creators note in the [associated paper](https://aclanthology.org/2022.naacl-main.194.pdf):
	> As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-parametric memory allows models to grow dramatically with a sub-linear increase in computational cost and GPU memory requirements. Recent models such as RAG and REALM have introduced retrieval into conditional generation. These models incorporate neural initial retrieval from a corpus of passages. We build on this line of research, proposing Re2G, which combines both neural initial retrieval and reranking into a BART-based sequence-to-sequence generation. Our reranking approach also permits merging retrieval results from sources with incomparable scores, enabling an ensemble of BM25 and neural initial retrieval. To train our system end-to-end, we introduce a novel variation of knowledge distillation to train the initial retrieval, reranker and generation using only ground truth on the target sequence output. We find large gains in four diverse tasks: zero-shot slot filling, question answering, fact checking and dialog, with relative gains of 9% to 34% over the previous state-of-the-art on the KILT leaderboard. We make our code available as open source.

	- Developed by: IBM
	- Shared by [Optional]: IBM

	- Model type: Query/Passage Reranker
	- Language(s) (NLP): English
	- License: Apache 2.0
	- Parent Model: [dpr-question_encoder-multiset-base](https://huggingface.co/facebook/dpr-question_encoder-multiset-base)
	- Resources for more information:
	- [GitHub Repo](https://github.com/IBM/kgi-slot-filling)
	- [Associated Paper](https://aclanthology.org/2022.naacl-main.194.pdf)


	# Uses


	## Direct Use
	This model can be used for the task of encoding a question to a vector to be used as a query into an Approximate Nearest Neighbors index. It must be used in combination with a context encoder that encodes passages to a vector and indexes them.


	# Citation


	BibTeX:

	```bibtex
	@inproceedings{glass-etal-2022-re2g,
	title = "{R}e2{G}: Retrieve, Rerank, Generate",
	author = "Glass, Michael and
	Rossiello, Gaetano and
	Chowdhury, Md Faisal Mahbub and
	Naik, Ankita and
	Cai, Pengshan and
	Gliozzo, Alfio",
	booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
	month = jul,
	year = "2022",
	address = "Seattle, United States",
	publisher = "Association for Computational Linguistics",
	url = "https://aclanthology.org/2022.naacl-main.194",
	doi = "10.18653/v1/2022.naacl-main.194",
	pages = "2701--2715",
	abstract = "As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-parametric memory allows models to grow dramatically with a sub-linear increase in computational cost and GPU memory requirements. Recent models such as RAG and REALM have introduced retrieval into conditional generation. These models incorporate neural initial retrieval from a corpus of passages. We build on this line of research, proposing Re2G, which combines both neural initial retrieval and reranking into a BART-based sequence-to-sequence generation. Our reranking approach also permits merging retrieval results from sources with incomparable scores, enabling an ensemble of BM25 and neural initial retrieval. To train our system end-to-end, we introduce a novel variation of knowledge distillation to train the initial retrieval, reranker and generation using only ground truth on the target sequence output. We find large gains in four diverse tasks: zero-shot slot filling, question answering, fact checking and dialog, with relative gains of 9{\%} to 34{\%} over the previous state-of-the-art on the KILT leaderboard. We make our code available as open source.",
	}

	```