An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving

Qinzhuo Wu, Qi Zhang, Zhongyu Wei


Abstract
Math word problem solving has attracted considerable research interest in recent years. Previous works have shown the effectiveness of utilizing graph neural networks to capture the relationships in the problem. However, these works did not carefully take the edge label information and the long-range word relationship across sentences into consideration. In addition, during generation, they focus on the most relevant areas of the currently generated word, while neglecting the rest of the problem. In this paper, we propose a novel Edge-Enhanced Hierarchical Graph-to-Tree model (EEH-G2T), in which the math word problems are represented as edge-labeled graphs. Specifically, an edge-enhanced hierarchical graph encoder is used to incorporate edge label information. This encoder updates the graph nodes hierarchically in two steps: sentence-level aggregation and problem-level aggregation. Furthermore, a tree-structured decoder with a split attention mechanism is applied to guide the model to pay attention to different parts of the input problem. Experimental results on the MAWPS and Math23K dataset showed that our EEH-G2T can effectively improve performance compared with state-of-the-art methods.
Anthology ID:
2021.findings-emnlp.127
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1473–1482
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.127
DOI:
10.18653/v1/2021.findings-emnlp.127
Bibkey:
Cite (ACL):
Qinzhuo Wu, Qi Zhang, and Zhongyu Wei. 2021. An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1473–1482, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving (Wu et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2021.findings-emnlp.127.pdf
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2021.findings-emnlp.127.mp4
Code
 qinzhuowu/eeh_g2t
Data
MAWPSMath23K