Long Context Question Answering via Supervised Contrastive Learning

Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan


Abstract
Long-context question answering (QA) tasks require reasoning over a long document or multiple documents. Addressing these tasks often benefits from identifying a set of evidence spans (e.g., sentences), which provide supporting evidence for answering the question.In this work, we propose a novel method for equipping long-context QA models with an additional sequence-level objective for better identification of the supporting evidence.We achieve this via an additional contrastive supervision signal in finetuning, where the model is encouraged to explicitly discriminate supporting evidence sentences from negative ones by maximizing question-evidence similarity. The proposed additional loss exhibits consistent improvements on three different strong long-context transformer models, across two challenging question answering benchmarks – HotpotQA and QAsper.
Anthology ID:
2022.naacl-main.207
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2872–2879
Language:
URL:
https://aclanthology.org/2022.naacl-main.207
DOI:
10.18653/v1/2022.naacl-main.207
Bibkey:
Cite (ACL):
Avi Caciularu, Ido Dagan, Jacob Goldberger, and Arman Cohan. 2022. Long Context Question Answering via Supervised Contrastive Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2872–2879, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Long Context Question Answering via Supervised Contrastive Learning (Caciularu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.207.pdf
Data
HotpotQAQASPER