Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

Vikas Yadav, Steven Bethard, Mihai Surdeanu


Abstract
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) stops when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.
Anthology ID:
2020.acl-main.414
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4514–4525
Language:
URL:
https://aclanthology.org/2020.acl-main.414
DOI:
10.18653/v1/2020.acl-main.414
Bibkey:
Cite (ACL):
Vikas Yadav, Steven Bethard, and Mihai Surdeanu. 2020. Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4514–4525, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering (Yadav et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.414.pdf
Video:
 http://slideslive.com/38929306
Code
 vikas95/AIR-retriever
Data
HotpotQAMultiRCQASCSuperGLUE