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
- 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)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.494.pdf
- Code
- nju-websoft/adalogn
- Data
- LogiQA, ReClor