Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning

被引:0
|
作者
Liu, Jiayu [1 ,2 ,3 ]
Huang, Zhenya [1 ,2 ,3 ]
Zhai, Chengxiang [4 ]
Liu, Qi [1 ,2 ,3 ]
机构
[1] Univ Sci & Technol China, Sch Data Sci, Anhui Prov Key Lab Big Data Anal & Applicat, Hefei, Peoples R China
[2] Univ Sci & Technol China, Sch Comp Sci & Technol, Hefei, Peoples R China
[3] Univ Illinois, State Key Lab Cognit Intelligence, Champaign, IL USA
[4] Univ Illinois, Champaign, IL USA
来源
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4 | 2023年
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Mathematical reasoning is one of the crucial abilities of general artificial intelligence, which requires machines to master mathematical logic and knowledge from solving problems. However, existing approaches are not transparent (thus not interpretable) in terms of what knowledge has been learned and applied in the reasoning process. In this paper, we propose a general Learning by Applying (LeAp) framework to enhance existing models (backbones) in a principled way by explicit knowledge learning. In LeAp, we perform knowledge learning in a novel problem-knowledge-expression paradigm, with a Knowledge Encoder to acquire knowledge from problem data and a Knowledge Decoder to apply knowledge for expression reasoning. The learned mathematical knowledge, including word-word relations and word-operator relations, forms an explicit knowledge graph, which bridges the knowledge "learning" and "applying" organically. Moreover, for problem solving, we design a semantics-enhanced module and a reasoning-enhanced module that apply knowledge to improve the problem comprehension and symbol reasoning abilities of any backbone, respectively. We theoretically prove the superiority of LeAp's autonomous learning mechanism. Experiments on three real-world datasets show that LeAp improves all backbones' performances, learns accurate knowledge, and achieves a more interpretable reasoning process.
引用
收藏
页码:4497 / 4506
页数:10
相关论文
共 50 条
  • [41] Causal Reinforcement Learning for Knowledge Graph Reasoning
    Li, Dezhi
    Lu, Yunjun
    Wu, Jianping
    Zhou, Wenlu
    Zeng, Guangjun
    APPLIED SCIENCES-BASEL, 2024, 14 (06):
  • [42] Judicial Knowledge Reasoning Based on Representation Learning
    Chen, Baogui
    Li, Zhuoyang
    Shen, Siyuan
    Zou, Zhipeng
    He, Tieke
    2019 COMPANION OF THE 19TH IEEE INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY (QRS-C 2019), 2019, : 84 - 88
  • [43] Learning to walk with logical embedding for knowledge reasoning
    Liu R.
    Yin G.
    Liu Z.
    Information Sciences, 2024, 667
  • [44] Tacit knowledge, implicit learning and scientific reasoning
    Pozzali A.
    Mind & Society, 2008, 7 (2) : 227 - 237
  • [45] Learning Contextualized Knowledge Structures for Commonsense Reasoning
    Yan, Jun
    Raman, Mrigank
    Chan, Aaron
    Zhang, Tianyu
    Rossi, Ryan
    Zhao, Handong
    Kim, Sungchul
    Lipka, Nedim
    Ren, Xiang
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 4038 - 4051
  • [46] 3D GEOMETRY AND LEARNING OF MATHEMATICAL REASONING
    Mithalal, Joris
    CERME 6 - PROCEEDINGS OF THE 6TH CONGRESS OF THE EUROPEAN SOCIETY FOR RESEARCH IN MATHEMATICS EDUCATION, 2010, : 796 - 805
  • [47] LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
    Wu, Yuhuai
    Rabe, Markus
    Li, Wenda
    Ba, Jimmy
    Grosse, Roger
    Szegedy, Christian
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [48] Shades of Knowledge-Infused Learning for Enhancing Deep Learning
    Sheth, Amit
    Gaur, Manas
    Kursuncu, Ugur
    Wickramarachchi, Ruwan
    IEEE INTERNET COMPUTING, 2019, 23 (06) : 54 - 63
  • [49] TOWARDS MATHEMATICAL REASONING: A MULTIMODAL DEEP LEARNING APPROACH
    Sinha, Abhishek
    Ayush, Kumar
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 4028 - 4032
  • [50] Enhancing learning resources reusability with a new learning design framework
    Yang, SJH
    Chang, ACN
    Chen, IYL
    5th IEEE International Conference on Advanced Learning Technologies, Proceedings, 2005, : 414 - 418