Complementary Evidence Identification in Open-Domain Question Answering

Xiangyang Mou, Mo Yu, Shiyu Chang, Yufei Feng, Li Zhang, Hui Su


Abstract
This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA). The problem aims to efficiently find a small set of passages that covers full evidence from multiple aspects as to answer a complex question. To this end, we proposes a method that learns vector representations of passages and models the sufficiency and diversity within the selected set, in addition to the relevance between the question and passages. Our experiments demonstrate that our method considers the dependence within the supporting evidence and significantly improves the accuracy of complementary evidence selection in QA domain.
Anthology ID:
2021.eacl-main.234
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2720–2726
Language:
URL:
https://aclanthology.org/2021.eacl-main.234
DOI:
10.18653/v1/2021.eacl-main.234
Bibkey:
Cite (ACL):
Xiangyang Mou, Mo Yu, Shiyu Chang, Yufei Feng, Li Zhang, and Hui Su. 2021. Complementary Evidence Identification in Open-Domain Question Answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2720–2726, Online. Association for Computational Linguistics.
Cite (Informal):
Complementary Evidence Identification in Open-Domain Question Answering (Mou et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2021.eacl-main.234.pdf
Data
HotpotQAMultiNLI