Related papers: FGeo-HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network

FGeo-HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network

URL: http://arxiv.org/abs/2402.11461v2
Date: Mon, 22 Apr 2024 07:31:15 GMT
Title: FGeo-HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network
Authors: Xiaokai Zhang, Na Zhu, Cheng Qin, Yang Li, Zhenbing Zeng, Tuo Leng,
Abstract summary: We build a neural-symbolic system to automatically perform human-like geometric deductive reasoning. We achieved a step-wised accuracy of 87.65% and an overall accuracy of 85.53% on the formalgeo7k datasets.
Score: 2.897954624664043
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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.

Related papers

Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram [78.79651421493058]
We propose a neural-symbolic model for plane geometry problem solving (PGPS) with three key steps: modal fusion, reasoning process and knowledge verification. For reasoning, we design an explicable solution program to describe the geometric reasoning process, and employ a self-limited decoder to generate solution program autoregressively. We also construct a large-scale geometry problem dataset called PGPS9K, containing fine-grained annotations of textual clauses, solution program and involved knowledge solvers.
arXiv Detail & Related papers (2024-07-10T02:45:22Z)
FGeo-DRL: Deductive Reasoning for Geometric Problems through Deep Reinforcement Learning [1.137457877869062]
We build a neural-symbolic system, called FGeoDRL, to automatically perform human-like geometric deductive reasoning. The neural part is an AI agent based on reinforcement learning, capable of autonomously learning problem-solving methods. Experiments conducted on the formalgeo7k dataset have achieved a problem-solving success rate of 86.40%.
arXiv Detail & Related papers (2024-02-14T09:48:39Z)
FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems [1.137457877869062]
We introduce FGeo-TP (Theorem Predictor), which utilizes the language model to predict theorem sequences for solving geometry problems. Our results demonstrate a significant increase in the problem-solving rate of the language model-enhanced FGeo-TP on the FormalGeo7k dataset.
arXiv Detail & Related papers (2024-02-14T09:44:28Z)
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries [77.04220651098723]
This paper presents the first attempt to represent geodesics on 3D mesh models using neural implicit functions. Specifically, we introduce neural geodesic fields (NeuroGFs), which are learned to represent the all-pairs geodesics of a given mesh. NeuroGFs exhibit exceptional performance in solving the single-source all-destination (SSAD) and point-to-point geodesics.
arXiv Detail & Related papers (2023-06-01T13:32:21Z)
On the Expressiveness and Generalization of Hypergraph Neural Networks [77.65788763444877]
This extended abstract describes a framework for analyzing the expressiveness, learning, and (structural) generalization of hypergraph neural networks (HyperGNNs) Specifically, we focus on how HyperGNNs can learn from finite datasets and generalize structurally to graph reasoning problems of arbitrary input sizes.
arXiv Detail & Related papers (2023-03-09T18:42:18Z)
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning [172.36214872466707]
We focus on solving geometric problems, which requires a comprehensive understanding of textual descriptions, visual diagrams, and theorem knowledge. We propose a Geometric Question Answering dataset GeoQA, containing 5,010 geometric problems with corresponding annotated programs.
arXiv Detail & Related papers (2021-05-30T12:34:17Z)
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning [123.06420835072225]
We construct a new large-scale benchmark, Geometry3K, consisting of 3,002 geometry problems with dense annotation in formal language. We propose a novel geometry solving approach with formal language and symbolic reasoning, called Interpretable Geometry Problem solver (Inter-GPS) Inter-GPS incorporates theorem knowledge as conditional rules and performs symbolic reasoning step by step.
arXiv Detail & Related papers (2021-05-10T07:46:55Z)
A neural anisotropic view of underspecification in deep learning [60.119023683371736]
We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
arXiv Detail & Related papers (2021-04-29T14:31:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.