Improving Commonsense Contingent Reasoning by Pseudo-data and Its Application to the Related Tasks

Kazumasa Omura, Sadao Kurohashi


Abstract
Contingent reasoning is one of the essential abilities in natural language understanding, and many language resources annotated with contingent relations have been constructed. However, despite the recent advances in deep learning, the task of contingent reasoning is still difficult for computers. In this study, we focus on the reasoning of contingent relation between basic events. Based on the existing data construction method, we automatically generate large-scale pseudo-problems and incorporate the generated data into training. We also investigate the generality of contingent knowledge through quantitative evaluation by performing transfer learning on the related tasks: discourse relation analysis, the Japanese Winograd Schema Challenge, and the JCommonsenseQA. The experimental results show the effectiveness of utilizing pseudo-problems for both the commonsense contingent reasoning task and the related tasks, which suggests the importance of contingent reasoning.
Anthology ID:
2022.coling-1.68
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
812–823
Language:
URL:
https://aclanthology.org/2022.coling-1.68
DOI:
Bibkey:
Cite (ACL):
Kazumasa Omura and Sadao Kurohashi. 2022. Improving Commonsense Contingent Reasoning by Pseudo-data and Its Application to the Related Tasks. In Proceedings of the 29th International Conference on Computational Linguistics, pages 812–823, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Improving Commonsense Contingent Reasoning by Pseudo-data and Its Application to the Related Tasks (Omura & Kurohashi, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.68.pdf
Data
CC100COPACommonsenseQAConceptNetSuperGLUEWSC