Abstract
With the advancements in natural language processing tasks, math word problem solving has received increasing attention. Previous methods have achieved promising results but ignore background common-sense knowledge not directly provided by the problem. In addition, during generation, they focus on local features while neglecting global information. To incorporate external knowledge and global expression information, we propose a novel knowledge-aware sequence-to-tree (KA-S2T) network in which the entities in the problem sequences and their categories are modeled as an entity graph. Based on this entity graph, a graph attention network is used to capture knowledge-aware problem representations. Further, we use a tree-structured decoder with a state aggregation mechanism to capture the long-distance dependency and global expression information. Experimental results on the Math23K dataset revealed that the KA-S2T model can achieve better performance than previously reported best results.- Anthology ID:
- 2020.emnlp-main.579
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7137–7146
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.579
- DOI:
- 10.18653/v1/2020.emnlp-main.579
- Cite (ACL):
- Qinzhuo Wu, Qi Zhang, Jinlan Fu, and Xuanjing Huang. 2020. A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7137–7146, Online. Association for Computational Linguistics.
- Cite (Informal):
- A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving (Wu et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2020.emnlp-main.579.pdf