Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text

Siyuan Wang, Wanjun Zhong, Duyu Tang, Zhongyu Wei, Zhihao Fan, Daxin Jiang, Ming Zhou, Nan Duan


Abstract
Logical reasoning of text requires identifying critical logical structures in the text and performing inference over them. Existing methods for logical reasoning mainly focus on contextual semantics of text while struggling to explicitly model the logical inference process. In this paper, we not only put forward a logic-driven context extension framework but also propose a logic-driven data augmentation algorithm. The former follows a three-step reasoning paradigm, and each step is respectively to extract logical expressions as elementary reasoning units, symbolically infer the implicit expressions following equivalence laws and extend the context to validate the options. The latter augments literally similar but logically different instances and incorporates contrastive learning to better capture logical information, especially logical negative and conditional relationships. We conduct experiments on two benchmark datasets, ReClor and LogiQA. The results show that our method achieves state-of-the-art performance on both datasets, and even surpasses human performance on the ReClor dataset.
Anthology ID:
2022.findings-acl.127
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1619–1629
Language:
URL:
https://aclanthology.org/2022.findings-acl.127
DOI:
10.18653/v1/2022.findings-acl.127
Bibkey:
Cite (ACL):
Siyuan Wang, Wanjun Zhong, Duyu Tang, Zhongyu Wei, Zhihao Fan, Daxin Jiang, Ming Zhou, and Nan Duan. 2022. Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1619–1629, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text (Wang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.127.pdf
Software:
 2022.findings-acl.127.software.zip
Code
 WangsyGit/LReasoner +  additional community code
Data
ReClor