Diagram Understanding in Geometry Questions

Author:

Seo Min Joon,Hajishirzi Hannaneh,Farhadi Ali,Etzioni Oren

Abstract

Automatically solving geometry questions is a long-standing AI problem. A geometry question typically includes a textual description accompanied by a diagram. The first step in solving geometry questions is diagram understanding, which consists of identifying visual elements in the diagram, their locations, their geometric properties, and aligning them to corresponding textual descriptions. In this paper, we present a method for diagram understanding that identifies visual elements in a diagram while maximizing agreement between textual and visual data. We show that the method's objective function is submodular; thus we are able to introduce an efficient method for diagram understanding that is close to optimal. To empirically evaluate our method, we compile a new dataset of geometry questions (textual descriptions and diagrams) and compare with baselines that utilize standard vision techniques. Our experimental evaluation shows an F1 boost of more than 17% in identifying visual elements and 25% in aligning visual elements with their textual descriptions.

Publisher

Association for the Advancement of Artificial Intelligence (AAAI)

Subject

General Medicine

Cited by 18 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Automated Generation of Geometry Proof Problems Based on Point Geometry Identity;Journal of Automated Reasoning;2024-06

2. Figuring Figures: An assessment of large language models on different modalities of math word problems;2024 9th International Conference on Machine Learning Technologies (ICMLT);2024-05-24

3. FGeo-SSS: A Search-Based Symbolic Solver for Human-like Automated Geometric Reasoning;Symmetry;2024-03-30

4. A Precise Text-to-Diagram Generation Method for Elementary Geometry;2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP);2023-12-15

5. SUFFI-GPSC: Sufficient Geometry Problem Solution Checking with Symbolic Computation and Logical Reasoning;2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP);2023-12-15

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3