Abstract
Ensuring both interpretability and correctness is a great challenge in automated geometry problem solving (GPS), and the scarcity of labeled data hinders learning mathematical reasoning from samples. Therefore, we present GeoDRL, a self-learning geometry problem solving framework that integrates logic graph deduction and Deep Reinforcement Learning (DRL) to optimize geometry reasoning as a Markov Decision Process. GeoDRL employs a Graph Neural Network on a Geometry Logic Graph, updating the problem state using a symbolic system. Incorporating DRL into deductive reasoning enables GeoDRL to achieve unsupervised self-learning while maintaining correctness. GeoDRL, through unsupervised learning, exhibits enhanced accuracy in the Geometry3K dataset, improving by 11.1% over previous SOTA methods, and simultaneously boosts efficiency and interpretability.- Anthology ID:
- 2023.findings-acl.850
- 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:
- 13468–13480
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.850
- DOI:
- 10.18653/v1/2023.findings-acl.850
- Cite (ACL):
- Shuai Peng, Di Fu, Yijun Liang, Liangcai Gao, and Zhi Tang. 2023. GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive Reasoning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13468–13480, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive Reasoning (Peng et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-acl.850.pdf