Recall and Learn: A Memory-augmented Solver for Math Word Problems

Shifeng Huang, Jiawei Wang, Jiao Xu, Da Cao, Ming Yang


Abstract
In this article, we tackle the math word problem, namely, automatically answering a mathematical problem according to its textual description. Although recent methods have demonstrated their promising results, most of these methods are based on template-based generation scheme which results in limited generalization capability. To this end, we propose a novel human-like analogical learning method in a recall and learn manner. Our proposed framework is composed of modules of memory, representation, analogy, and reasoning, which are designed to make a new exercise by referring to the exercises learned in the past. Specifically, given a math word problem, the model first retrieves similar questions by a memory module and then encodes the unsolved problem and each retrieved question using a representation module. Moreover, to solve the problem in a way of analogy, an analogy module and a reasoning module with a copy mechanism are proposed to model the interrelationship between the problem and each retrieved question. Extensive experiments on two well-known datasets show the superiority of our proposed algorithm as compared to other state-of-the-art competitors from both overall performance comparison and micro-scope studies.
Anthology ID:
2021.findings-emnlp.68
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
786–796
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.68
DOI:
10.18653/v1/2021.findings-emnlp.68
Bibkey:
Cite (ACL):
Shifeng Huang, Jiawei Wang, Jiao Xu, Da Cao, and Ming Yang. 2021. Recall and Learn: A Memory-augmented Solver for Math Word Problems. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 786–796, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Recall and Learn: A Memory-augmented Solver for Math Word Problems (Huang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.68.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.68.mp4
Code
 sfeng-m/real4mwp
Data
Math23K