Analogical Math Word Problems Solving with Enhanced Problem-Solution Association

Zhenwen Liang, Jipeng Zhang, Xiangliang Zhang


Abstract
Math word problem (MWP) solving is an important task in question answering which requires human-like reasoning ability. Analogical reasoning has long been used in mathematical education, as it enables students to apply common relational structures of mathematical situations to solve new problems. In this paper, we propose to build a novel MWP solver by leveraging analogical MWPs, which advance the solver’s generalization ability across different kinds of MWPs. The key idea, named analogy identification, is to associate the analogical MWP pairs in a latent space, i.e., encoding an MWP close to another analogical MWP, while leaving away from the non-analogical ones. Moreover, a solution discriminator is integrated into the MWP solver to enhance the association between an MWP and its true solution. The evaluation results verify that our proposed analogical learning strategy promotes the performance of MWP-BERT on Math23k over the state-of-the-art model Generate2Rank, with 5 times fewer parameters in the encoder. We also find that our model has a stronger generalization ability in solving difficult MWPs due to the analogical learning from easy MWPs.
Anthology ID:
2022.emnlp-main.643
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9454–9464
Language:
URL:
https://aclanthology.org/2022.emnlp-main.643
DOI:
10.18653/v1/2022.emnlp-main.643
Bibkey:
Cite (ACL):
Zhenwen Liang, Jipeng Zhang, and Xiangliang Zhang. 2022. Analogical Math Word Problems Solving with Enhanced Problem-Solution Association. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9454–9464, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Analogical Math Word Problems Solving with Enhanced Problem-Solution Association (Liang et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.643.pdf