Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems

Yibin Shen, Qianying Liu, Zhuoyuan Mao, Zhen Wan, Fei Cheng, Sadao Kurohashi


Abstract
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution equation supervised by human annotation. In this paper, we propose a controlled equation generation solver by leveraging a set of control codes to guide the model to consider certain reasoning logic and decode the corresponding equations expressions transformed from the human reference. The empirical results suggest that our method universally improves the performance on single-unknown (Math23K) and multiple-unknown (DRAW1K, HMWP) benchmarks, with substantial improvements up to 13.2% accuracy on the challenging multiple-unknown datasets.
Anthology ID:
2022.aacl-short.32
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
254–260
Language:
URL:
https://aclanthology.org/2022.aacl-short.32
DOI:
Bibkey:
Cite (ACL):
Yibin Shen, Qianying Liu, Zhuoyuan Mao, Zhen Wan, Fei Cheng, and Sadao Kurohashi. 2022. Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 254–260, Online only. Association for Computational Linguistics.
Cite (Informal):
Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems (Shen et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.aacl-short.32.pdf