When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions

ZiXian Huang, Ao Wu, Yulin Shen, Gong Cheng, Yuzhong Qu


Abstract
Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description. Since a scenario contains both keyphrases for retrieval and much noise, retrieval for SQA is extremely difficult. Moreover, it can hardly be supervised due to the lack of relevance labels of paragraphs for SQA. To meet the challenge, in this paper we propose a joint retriever-reader model called JEEVES where the retriever is implicitly supervised only using QA labels via a novel word weighting mechanism. JEEVES significantly outperforms a variety of strong baselines on multiple-choice questions in three SQA datasets.
Anthology ID:
2021.findings-emnlp.84
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
985–994
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.84
DOI:
10.18653/v1/2021.findings-emnlp.84
Bibkey:
Cite (ACL):
ZiXian Huang, Ao Wu, Yulin Shen, Gong Cheng, and Yuzhong Qu. 2021. When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 985–994, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions (Huang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.84.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.84.mp4
Code
 nju-websoft/jeeves-gkmc