Clues Before Answers: Generation-Enhanced Multiple-Choice QA

Zixian Huang, Ao Wu, Jiaying Zhou, Yu Gu, Yue Zhao, Gong Cheng


Abstract
A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework. By unifying data in different tasks into a single text-to-text format, it trains a generative encoder-decoder model which is both powerful and universal. However, a side effect of twisting a generation target to fit the classification nature of MCQA is the under-utilization of the decoder and the knowledge that can be decoded. To exploit the generation capability and underlying knowledge of a pre-trained encoder-decoder model, in this paper, we propose a generation-enhanced MCQA model named GenMC. It generates a clue from the question and then leverages the clue to enhance a reader for MCQA. It outperforms text-to-text models on multiple MCQA datasets.
Anthology ID:
2022.naacl-main.239
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
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3272–3287
Language:
URL:
https://aclanthology.org/2022.naacl-main.239
DOI:
10.18653/v1/2022.naacl-main.239
Bibkey:
Cite (ACL):
Zixian Huang, Ao Wu, Jiaying Zhou, Yu Gu, Yue Zhao, and Gong Cheng. 2022. Clues Before Answers: Generation-Enhanced Multiple-Choice QA. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3272–3287, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Clues Before Answers: Generation-Enhanced Multiple-Choice QA (Huang et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.239.pdf
Video:
 https://aclanthology.org/2022.naacl-main.239.mp4
Code
 nju-websoft/genmc
Data
CommonsenseQAOpenBookQAQASC