OPERA: Operation-Pivoted Discrete Reasoning over Text

Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao


Abstract
Machine reading comprehension (MRC) that requires discrete reasoning involving symbolic operations, e.g., addition, sorting, and counting, is a challenging task. According to this nature, semantic parsing-based methods predict interpretable but complex logical forms. However, logical form generation is nontrivial and even a little perturbation in a logical form will lead to wrong answers. To alleviate this issue, multi-predictor -based methods are proposed to directly predict different types of answers and achieve improvements. However, they ignore the utilization of symbolic operations and encounter a lack of reasoning ability and interpretability. To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability. Specifically, operations are first selected and then softly executed to simulate the answer reasoning procedure. Extensive experiments on both DROP and RACENum datasets show the reasoning ability of OPERA. Moreover, further analysis verifies its interpretability.
Anthology ID:
2022.naacl-main.119
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:
1655–1666
Language:
URL:
https://aclanthology.org/2022.naacl-main.119
DOI:
10.18653/v1/2022.naacl-main.119
Bibkey:
Cite (ACL):
Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, and Tiejun Zhao. 2022. OPERA: Operation-Pivoted Discrete Reasoning over Text. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1655–1666, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
OPERA: Operation-Pivoted Discrete Reasoning over Text (Zhou et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.119.pdf
Video:
 https://aclanthology.org/2022.naacl-main.119.mp4
Code
 jd-ai-research-nlp/opera
Data
DROPRACE