Double Retrieval and Ranking for Accurate Question Answering

Zeyu Zhang, Thuy Vu, Alessandro Moschitti


Abstract
Recent work has shown that an answer verification step introduced in Transformer-based answer selection models can significantly improve the state of the art in Question Answering. This step is performed by aggregating the embeddings of top k answer candidates to support the verification of a target answer. Although the approach is intuitive and sound, it still shows two limitations: (i) the supporting candidates are ranked only according to the relevancy with the question and not with the answer, and (ii) the support provided by the other answer candidates is suboptimal as these are retrieved independently of the target answer. In this paper, we address both drawbacks by proposing (i) a double reranking model, which, for each target answer, selects the best support; and (ii) a second neural retrieval stage designed to encode question and answer pair as the query, which finds more specific verification information. The results on well-known datasets for Answer Sentence Selection show significant improvement over the state of the art.
Anthology ID:
2023.findings-eacl.130
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1751–1762
Language:
URL:
https://aclanthology.org/2023.findings-eacl.130
DOI:
10.18653/v1/2023.findings-eacl.130
Bibkey:
Cite (ACL):
Zeyu Zhang, Thuy Vu, and Alessandro Moschitti. 2023. Double Retrieval and Ranking for Accurate Question Answering. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1751–1762, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Double Retrieval and Ranking for Accurate Question Answering (Zhang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.130.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.130.mp4