Analogical Math Word Problems Solving with Enhanced Problem-Solution Association

Zhenwen Liang, Jipeng Zhang, Xiangliang Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

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 moving away from the non-analogical ones. Moreover, a solution discriminator is integrated into the MWP solver to enhance the association between the representations of MWPs and their true solutions. 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.
Original languageEnglish (US)
Title of host publicationProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
PublisherAssociation for Computational Linguistics (ACL)
Pages9454-9464
Number of pages11
StatePublished - Jan 1 2022
Externally publishedYes

Fingerprint

Dive into the research topics of 'Analogical Math Word Problems Solving with Enhanced Problem-Solution Association'. Together they form a unique fingerprint.

Cite this