Number-enhanced representation with hierarchical recursive tree decoding for math word problem solving

被引:0
|
作者
Zhang, Yi [1 ]
Zhou, Guangyou [2 ,3 ]
Xie, Zhiwen [2 ,3 ]
Huang, Jimmy Xiangji [4 ]
机构
[1] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Hubei, Peoples R China
[2] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China
[3] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China
[4] York Univ, Sch Informat Technol, Toronto, ON, Canada
基金
中国国家自然科学基金;
关键词
Math word problem solving; Numerical reasoning; Tree decoder;
D O I
10.1016/j.ipm.2023.103585
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Automatic solving math word problems (MWPs) is a number-intensive application in natural language processing (NLP). However, these existing methods are far from achieving acceptable levels of numeracy learning. As a result, the performance of these models is limited for mathe-matical reasoning. In addition, the mainstream tree decoder suffers from early-stage information loss, resulting in an unsatisfactory performance for complex problems with more operators. In this paper, we propose NERHRT (Number-Enhanced Representation with Hierarchical Recursive Tree Decoding), a simple yet effective number embedding method that produces the numerical reasoning via the decimal notation-based embedding and a dual-direction graph attention network. In addition, a hierarchical recursive tree-structured decoder is introduced to aggregate information from all ancestor nodes. Experiments show that our approach obtains the best performance on four popular benchmark datasets, and beats the state-of-the-art models with a large margin.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] 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
  • [2] 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
  • [3] HMS: A Hierarchical Solver with Dependency-Enhanced Understanding for Math Word Problem
    Lin, Xin
    Huang, Zhenya
    Zhao, Hongke
    Chen, Enhong
    Liu, Qi
    Wang, Hao
    Wang, Shijin
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4232 - 4240
  • [4] A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving
    Wu, Qinzhuo
    Zhang, Qi
    Fu, Jinlan
    Huang, Xuanjing
    [J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 7137 - 7146
  • [5] Translating a Math Word Problem to a Expression Tree
    Wang, Lei
    Wang, Yan
    Cai, Deng
    Zhang, Dongxiang
    Liu, Xiaojiang
    [J]. 2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 1064 - 1069
  • [6] A Recursive tree-structured neural network with goal forgetting and information aggregation for solving math word problems
    Xiao, Jing
    Huang, Linjia
    Song, Yu
    Tang, Na
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (03)
  • [7] Graph-to-Tree Learning for Solving Math Word Problems
    Zhang, Jipeng
    Wang, Lei
    Lee, Roy Ka-Wei
    Bin, Yi
    Wang, Yan
    Shao, Jie
    Lim, Ee-Peng
    [J]. 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 3928 - 3937
  • [8] Math Word Problem Solving by Generating Linguistic Variants of Problem Statements
    Raiyan, Syed Rifat
    Faiyaz, Md. Nafis
    Kabir, Shah Md. Jawad
    Kabir, Mohsinul
    Mahmud, Hasan
    Hasan, Md. Kamrul
    [J]. PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-SRW 2023, VOL 4, 2023, : 362 - 378
  • [9] Problem Representation and Mathematical Problem Solving of Students of Varying Math Ability
    Krawec, Jennifer L.
    [J]. JOURNAL OF LEARNING DISABILITIES, 2014, 47 (02) : 103 - 115
  • [10] Solving Math Word Problem with External Knowledge and Entailment Loss
    Lu, Rizhongtian
    Tan, Yongmei
    Niu, Shaozhang
    Lin, Yunze
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT IX, 2023, 14262 : 320 - 331