Geometry Problem Solving Based on Counter-factual Evolutionary Reasoning

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Geometry Problem Solving Based on Counter-factual Evolutionary Reasoning
	Song B(宋冰)1,2 ; Xiong G(熊刚)1,3,4 ; Shen Z(沈震)3,5 ; Zhu F(朱凤华)1,4 ; Lv Y（吕宜生）1 ; Ye P（叶佩军）1
	2023
会议名称	2023 IEEE 19th International Conference on Automation Science and Engineering (CASE 2023)
会议日期	2023
会议地点	New Zealand
出版者	IEEE
摘要	As a representative topic in natural language processing and automated theorem proving, geometry prob lem solving requires an abstract problem understanding and symbolic reasoning. A major challenge here is to find a feasible reasoning sequence that is consistent with given axioms and the theorems already proved. Most recent methods have exploited neural network-based techniques to automatically discover eligible solving steps. Such a kind of methods, however, is greatly impacted by the expert solutions for training. To improve the accuracy, this paper proposes a new method called counterfactual evolutionary reasoning, which uses a generative adversarial network to generate initial reasoning sequences and then introduces counterfactual reasoning to explore potential solutions. By directly exploring theorem candidates rather than the neural network selection, the new method can sufficiently extend the searching space to get a more appropriate reasoning step. Through comparative experiments on the recent proposed Geometry3k, the largest geometry problem solving dataset, our method generally achieves a higher accuracy than most previous methods, bringing an overall improvement about 4.4% compared with the transformer models.
收录类别	EI
七大方向——子方向分类	自然语言处理
国重实验室规划方向分类	认知决策知识体系
是否有论文关联数据集需要存交	否
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/52160
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Ye P（叶佩军）
作者单位	1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.The Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation, Chinese Academy of Sciences, China 4.The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing, The Cloud Computing Center, Chinese Academy of Sciences, Dongguan 523808, China 5.Intelligent Manufacturing Center, Qingdao Academy of Intelligent Industries, Qingdao 266000, China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Song B,Xiong G,Shen Z,et al. Geometry Problem Solving Based on Counter-factual Evolutionary Reasoning[C]:IEEE,2023.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
CASE.pdf（1318KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载