Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems

Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin


Abstract
A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs while most existing works only focused on one-unknown linear MWPs. Herein, we propose a simple but efficient method called Universal Expression Tree (UET) to make the first attempt to represent the equations of various MWPs uniformly. Then a semantically-aligned universal tree-structured solver (SAU-Solver) based on an encoder-decoder framework is proposed to resolve multiple types of MWPs in a unified model, benefiting from our UET representation. Our SAU-Solver generates a universal expression tree explicitly by deciding which symbol to generate according to the generated symbols’ semantic meanings like human solving MWPs. Besides, our SAU-Solver also includes a novel subtree-level semanticallyaligned regularization to further enforce the semantic constraints and rationality of the generated expression tree by aligning with the contextual information. Finally, to validate the universality of our solver and extend the research boundary of MWPs, we introduce a new challenging Hybrid Math Word Problems dataset (HMWP), consisting of three types of MWPs. Experimental results on several MWPs datasets show that our model can solve universal types of MWPs and outperforms several state-of-the-art models.
Anthology ID:
2020.emnlp-main.309
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3780–3789
Language:
URL:
https://aclanthology.org/2020.emnlp-main.309
DOI:
10.18653/v1/2020.emnlp-main.309
Bibkey:
Cite (ACL):
Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, and Liang Lin. 2020. Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3780–3789, Online. Association for Computational Linguistics.
Cite (Informal):
Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems (Qin et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.309.pdf
Video:
 https://slideslive.com/38938662
Code
 QinJinghui/SAU-Solver
Data
ALG514MAWPSMath23K