AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension

Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun, Yuzhong Qu


Abstract
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.
Anthology ID:
2022.acl-long.494
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7147–7161
Language:
URL:
https://aclanthology.org/2022.acl-long.494
DOI:
10.18653/v1/2022.acl-long.494
Bibkey:
Cite (ACL):
Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun, and Yuzhong Qu. 2022. AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7147–7161, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension (Li et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.494.pdf
Software:
 2022.acl-long.494.software.zip
Code
 nju-websoft/adalogn
Data
LogiQAReClor