تقرير
FGeo-HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network
العنوان: | FGeo-HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network |
---|---|
المؤلفون: | Zhang, Xiaokai, Zhu, Na, Qin, Cheng, Li, Yang, Zeng, Zhenbing, Leng, Tuo |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Artificial Intelligence |
الوصف: | Geometric problem solving has always been a long-standing challenge in the fields of automated reasoning and artificial intelligence. We built a neural-symbolic system to automatically perform human-like geometric deductive reasoning. The symbolic part is a formal system built on FormalGeo, which can automatically perform geomertic relational reasoning and algebraic calculations and organize the solving process into a solution hypertree with conditions as hypernodes and theorems as hyperedges. The neural part, called HyperGNet, is a hypergraph neural network based on the attention mechanism, including a encoder to effectively encode the structural and semantic information of the hypertree, and a solver to provide problem-solving guidance. The neural part predicts theorems according to the hypertree, and the symbolic part applies theorems and updates the hypertree, thus forming a predict-apply cycle to ultimately achieve readable and traceable automatic solving of geometric problems. Experiments demonstrate the correctness and effectiveness of this neural-symbolic architecture. We achieved a step-wised accuracy of 87.65% and an overall accuracy of 85.53% on the formalgeo7k datasets. Comment: 13 pages |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2402.11461 |
رقم الأكسشن: | edsarx.2402.11461 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |