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
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
  • [1] A collaborative learning framework for knowledge graph embedding and reasoning
    Wang, Hao
    Song, Dandan
    Wu, Zhijing
    Li, Jia
    Zhou, Yanru
    Xu, Jing
    KNOWLEDGE-BASED SYSTEMS, 2024, 289
  • [2] A Cognitive Solver with Autonomously Knowledge Learning for Reasoning Mathematical Answers
    Liu, Jiayu
    Huang, Zhenya
    Lin, Xin
    Liu, Qi
    Ma, Jianhui
    Chen, Enhong
    2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2022, : 269 - 278
  • [3] Enhancing Knowledge Management via Organizational Learning
    Pei, Ng Sin
    CREATING GLOBAL ECONOMIES THROUGH INNOVATION AND KNOWLEDGE MANAGEMENT: THEORY & PRACTICE, VOLS 1-3, 2009, : 591 - 595
  • [4] Enhancing mathematical reasoning in the classroom: The effects of cooperative learning and metacognitive training
    Kramarski, B
    Mevarech, ZR
    AMERICAN EDUCATIONAL RESEARCH JOURNAL, 2003, 40 (01) : 281 - 310
  • [5] KE: A Knowledge Enhancing Framework for Machine Learning Models
    Wang, Yijue
    Shah, Nidhibahen
    Soliman, Ahmed
    Guo, Dan
    Rajasekaran, Sanguthevar
    JOURNAL OF PHYSICAL CHEMISTRY A, 2023, 127 (40): : 8437 - 8446
  • [6] Dynamic Decision Making Based on Explicit Knowledge Reasoning and Deep Reinforcement Learning
    Zhang H.-D.
    Chen Z.-H.
    Chen J.-Y.
    Zhou Y.
    Lian D.-F.
    Wu K.-S.
    Lin F.-Z.
    Ruan Jian Xue Bao/Journal of Software, 2023, 34 (08): : 3821 - 3835
  • [7] AN INTEGRATED FRAMEWORK FOR LEARNING AND REASONING
    GIRAUDCARRIER, CG
    MARTINEZ, TR
    JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 1995, 3 : 147 - 185
  • [8] DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning
    Li, Ruiping
    Cheng, Xiang
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 2642 - 2651
  • [9] Peano: learning formal mathematical reasoning
    Poesia, Gabriel
    Goodman, Noah D.
    PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2023, 381 (2251):
  • [10] A Survey of Deep Learning for Mathematical Reasoning
    Lu, Pan
    Qiu, Liang
    Yu, Wenhao
    Welleck, Sean
    Chang, Kai-Wei
    PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023): LONG PAPERS, VOL 1, 2023, : 14605 - 14631