LANS: A Layout-Aware Neural Solver for Plane Geometry Problem

2023/11/25 by Zhongzhi Li, Mingliang Zhang, Li, Zhong-Zhi +5 · 6 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Image and Object Detection Techniques #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2311.16476

openalex publication_date 2023/11/25 · openalex created_date 2023/11/30 · openalex updated_date 2026/07/28

Abstract

Geometry problem solving (GPS) is a challenging mathematical reasoning task requiring multi-modal understanding, fusion, and reasoning. Existing neural solvers take GPS as a vision-language task but are short in the representation of geometry diagrams that carry rich and complex layout information. In this paper, we propose a layout-aware neural solver named LANS, integrated with two new modules: multimodal layout-aware pre-trained language module (MLA-PLM) and layout-aware fusion attention (LA-FA). MLA-PLM adopts structural-semantic pre-training (SSP) to implement global relationship modeling, and point-match pre-training (PMP) to achieve alignment between visual points and textual points. LA-FA employs a layout-aware attention mask to realize point-guided cross-modal fusion for further boosting layout awareness of LANS. Extensive experiments on datasets Geometry3K and PGPS9K validate the effectiveness of the layout-aware modules and superior problem-solving performance of our LANS solver, over existing symbolic and neural solvers. The code will be made public available soon.

Cited by

• GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Language
• Non-Parametric Structural Priors for Geometry Theorem Prediction
• A Survey of Deep Learning for Geometry Problem Solving
• AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
• Large Language Models as Computable Approximations to Solomonoff Induction
• Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey

Related

• A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram
• Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram
• Towards Geometry Problem Solving in the Large Model Era: A Survey
• AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
• Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration