Compositional Mathematical Encoding for Math Word Problems
Zhenwen Liang, Jipeng Zhang, Kehan Guo, Xiaodong Wu, Jie Shao, Xiangliang Zhang
Abstract
Solving math word problem (MWP) remains a challenging task, as it requires to understand both the semantic meanings of the text and the mathematical logic among quantities, i.e., for both semantics modal and quantity modal learning. Current MWP encoders work in a uni-modal setting and map the given problem description to a latent representation, then for decoding. The generalizability of these MWP encoders is thus limited because some problems are semantics-demanding and others are quantity-demanding. To address this problem, we propose a Compositional Math Word Problem Solver (C-MWP) which works in a bi-modal setting encoding in an interactive way. Extensive experiments validate the effectiveness of C-MWP and show its superiority over state-of-the-art models on public benchmarks.- Anthology ID:
- 2023.findings-acl.635
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10008–10017
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.635
- DOI:
- 10.18653/v1/2023.findings-acl.635
- Cite (ACL):
- Zhenwen Liang, Jipeng Zhang, Kehan Guo, Xiaodong Wu, Jie Shao, and Xiangliang Zhang. 2023. Compositional Mathematical Encoding for Math Word Problems. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10008–10017, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Compositional Mathematical Encoding for Math Word Problems (Liang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.findings-acl.635.pdf