HMS: A Hierarchical Solver with Dependency-Enhanced Understanding for Math Word Problem

被引:0
|
作者
Lin, Xin [1 ]
Huang, Zhenya [1 ]
Zhao, Hongke [2 ]
Chen, Enhong [1 ]
Liu, Qi [1 ]
Wang, Hao [1 ]
Wang, Shijin [3 ,4 ]
机构
[1] Univ Sci & Technol China, Sch Comp Sci & Technol, Anhui Prov Key Lab Big Data Anal & Applicat, Hefei, Peoples R China
[2] Tianjin Univ, Coll Management & Econ, Tianjin, Peoples R China
[3] iFLYTEK Res, Hefei, Peoples R China
[4] iFLYTEK Co Ltd, State Key Lab Cognit Intelligence, Hefei, Peoples R China
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
Automatically solving math word problems is a crucial task for exploring the intelligence levels of machines in the general AI domain. It is highly challenging since it requires not only natural language understanding but also mathematical expression inference. Existing solutions usually explore sequence-to-sequence models to generate expressions, where the problems are simply encoded sequentially. However, such models are generally far from enough for understanding problems as similar to humans and lead to incorrect answers. To this end, in this paper, we propose a novel Hierarchical Math Solver (HMS) to make deep understanding and exploitation of problems. In problem understanding, imitating human reading habits, we propose a hierarchical word-clauseproblem encoder. Specifically, we first split each problem into several clauses and learn problem semantics from the local clause level to the global problem level. Then, in clause understanding, we propose a dependency-based module to enhance clause semantics with the dependency structure of the problem. Next, in expression inference, we propose a novel tree-based decoder to generate the mathematical expression for the answer. In the decoder, we apply a hierarchical attention mechanism to enhance the problem semantics with context from different levels, and a pointer-generator network to guide the model to copy existing information and infer extra knowledge. Extensive experimental results on two widely used datasets demonstrate that HMS achieves not only better answers but also more reasonable inference.
引用
收藏
页码:4232 / 4240
页数:9
相关论文
共 11 条
  • [1] Learning Relation-Enhanced Hierarchical Solver for Math Word Problems
    Lin, Xin
    Huang, Zhenya
    Zhao, Hongke
    Chen, Enhong
    Liu, Qi
    Lian, Defu
    Li, Xin
    Wang, Hao
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 35 (10) : 1 - 15
  • [2] A Bi-Channel Math Word Problem Solver With Understanding and Reasoning
    Meng, Hao
    Yang, Ting
    Yu, Xinguo
    [J]. IEEE TALE2021: IEEE INTERNATIONAL CONFERENCE ON ENGINEERING, TECHNOLOGY AND EDUCATION, 2021, : 29 - 34
  • [3] An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving
    Wu, Qinzhuo
    Zhang, Qi
    Wei, Zhongyu
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 1473 - 1482
  • [4] Number-enhanced representation with hierarchical recursive tree decoding for math word problem solving
    Zhang, Yi
    Zhou, Guangyou
    Xie, Zhiwen
    Huang, Jimmy Xiangji
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (02)
  • [5] Enhancing Seq2seq Math Word Problem Solver with Entity Information and Math Knowledge
    Li, Lei
    Zhang, Dongxiang
    Wang, Chengyu
    Jin, Cheqing
    Gao, Ming
    Zhou, Aoying
    [J]. WEB INFORMATION SYSTEMS ENGINEERING - WISE 2022, 2022, 13724 : 370 - 385
  • [6] Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers
    Kumar, Vivek
    Maheshwary, Rishabh
    Pudi, Vikram
    [J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 4194 - 4206
  • [7] Math Word Problem Solver Based on Text-to-Text Transformer Model
    Yang, Chuanzhi
    Huang, Runze
    Yu, Xinguo
    Peng, Rao
    [J]. IEEE TALE2021: IEEE INTERNATIONAL CONFERENCE ON ENGINEERING, TECHNOLOGY AND EDUCATION, 2021, : 818 - 822
  • [8] A Math Word Problem Solver Based on Deep Adaptive Graph Convolutional Networks
    Jiang, Guisong
    Li, Shuang
    Zhang, Long
    [J]. 2022 4th International Conference on Frontiers Technology of Information and Computer, ICFTIC 2022, 2022, : 802 - 805
  • [9] HGEN: Learning Hierarchical Heterogeneous Graph Encoding for Math Word Problem Solving
    Zhang, Yi
    Zhou, Guangyou
    Xie, Zhiwen
    Huang, Jimmy Xiangji
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 30 : 816 - 828
  • [10] A Goal-Oriented Meaning-based Statistical Multi-Step Math Word Problem Solver with Understanding, Reasoning and Explanation (Demonstration)
    Liang, Chao-Chun
    Wong, Yu-Shiang
    Lin, Yi-Chung
    Su, Keh-Yih
    [J]. PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 5235 - 5237