You Only Need One Model for Open-domain Question Answering

Haejun Lee, Akhil Kedia, Jongwon Lee, Ashwin Paranjape, Christopher Manning, Kyoung-Gu Woo


Abstract
Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model. Despite performing related tasks, the models have separate parameters and are weakly-coupled during training. We propose casting the retriever and the reranker as internal passage-wise attention mechanisms applied sequentially within the transformer architecture and feeding computed representations to the reader, with the hidden representations progressively refined at each stage. This allows us to use a single question answering model trained end-to-end, which is a more efficient use of model capacity and also leads to better gradient flow. We present a pre-training method to effectively train this architecture and evaluate our model on the Natural Questions and TriviaQA open datasets. For a fixed parameter budget, our model outperforms the previous state-of-the-art model by 1.0 and 0.7 exact match scores.
Anthology ID:
2022.emnlp-main.198
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3047–3060
Language:
URL:
https://aclanthology.org/2022.emnlp-main.198
DOI:
10.18653/v1/2022.emnlp-main.198
Bibkey:
Cite (ACL):
Haejun Lee, Akhil Kedia, Jongwon Lee, Ashwin Paranjape, Christopher Manning, and Kyoung-Gu Woo. 2022. You Only Need One Model for Open-domain Question Answering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3047–3060, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
You Only Need One Model for Open-domain Question Answering (Lee et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.198.pdf