Chinese Named Entity Recognition for Automobile Fault Texts Based on External Context Retrieving and Adversarial Training

被引:0
作者
Wang, Shuhai [1 ,2 ]
Sun, Linfu [1 ,2 ]
机构
[1] Southwest Jiaotong Univ, Sch Comp & Artificial Intelligence, Chengdu 611756, Peoples R China
[2] Southwest Jiaotong Univ, Mfg Ind Chain Collaborat & Informat Support Techno, Chengdu 610031, Peoples R China
关键词
automobile fault text; named entity recognition; adversarial training; bidirectional long short-term memory; information entropy;
D O I
10.3390/e27020133
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Identifying key concepts in automobile fault texts is crucial for understanding fault causes and enabling diagnosis. However, effective mining tools are lacking, leaving much latent information unexplored. To solve the problem, this paper proposes Chinese named entity recognition for automobile fault texts based on external context retrieval and adversarial training. First, we retrieve external contexts by using a search engine. Then, the input sentence and its external contexts are respectively fed into Lexicon Enhanced BERT to improve the text embedding representation. Furthermore, the input sentence and its external contexts embedding representation are fused through the attention mechanism. Then, adversarial samples are generated by adding perturbations to the fusion vector representation. Finally, the fusion vector representation and adversarial samples are input into the BiLSTM-CRF layer as training data for entity labeling. Our model is evaluated on the automotive fault datasets, Weibo and Resume datasets, and achieves state-of-the-art results.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] Named Entity Recognition among Chinese MicroBlog Based on Cascaded CRF
    Xing, Yixue
    Zhu, Yonghua
    Zhang, Ke
    Liu, Shenkai
    Zhou, Jin
    2018 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING (ICALIP), 2018, : 28 - 34
  • [42] Chinese Named Entity Recognition of Geological News Based on BERT Model
    Huang, Chao
    Wang, Yuzhu
    Yu, Yuqing
    Hao, Yujia
    Liu, Yuebin
    Zhao, Xiujian
    APPLIED SCIENCES-BASEL, 2022, 12 (15):
  • [43] A Novel Method for Chinese Named Entity Recognition Based on Character Vector
    Lu, Jing
    Ye, Mao
    Tang, Zhi
    Huang, Xiao-Jun
    Ma, Jia-Le
    COLLABORATIVE COMPUTING: NETWORKING, APPLICATIONS, AND WORKSHARING, COLLABORATECOM 2015, 2016, 163 : 141 - 150
  • [44] A Chinese Medical Named Entity Recognition Method Based on Glyph Features
    Meng, Wei-Lun
    Guo, Jing-Feng
    Xing, Ke-Xuan
    Wei, Ning
    Wang, Qiao-Suo
    Liu, Bin
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2024, 52 (06): : 1945 - 1954
  • [45] Named Entity Recognition in Chinese Electronic Medical Records Based on CRF
    Liu, Kaixin
    Hu, Qingcheng
    Liu, Jianwei
    Xing, Chunxiao
    2017 14TH WEB INFORMATION SYSTEMS AND APPLICATIONS CONFERENCE (WISA 2017), 2017, : 105 - 110
  • [46] A Research Toward Chinese Named Entity Recognition Based on Transfer Learning
    Hui Kang
    Jingwu Xiao
    Yunpeng Zhang
    Lei Zhang
    Xu Zhao
    Tie Feng
    International Journal of Computational Intelligence Systems, 16
  • [47] CRF-based Active Learning for Chinese Named Entity Recognition
    Yao, Lin
    Sun, Chengjie
    Li, Shaofeng
    Wang, Xiaolong
    Wang, Xuan
    2009 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2009), VOLS 1-9, 2009, : 1557 - +
  • [48] Chinese Named Entity Recognition Based on Knowledge Based Question Answering System
    Yin, Didi
    Cheng, Siyuan
    Pan, Boxu
    Qiao, Yuanyuan
    Zhao, Wei
    Wang, Dongyu
    APPLIED SCIENCES-BASEL, 2022, 12 (11):
  • [49] Chinese Named Entity Recognition Based on Improved K-BERT
    Li, Jianli
    Yilahun, Hankiz
    Hamdulla, Askar
    2022 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, HUMAN-COMPUTER INTERACTION AND ARTIFICIAL INTELLIGENCE, VRHCIAI, 2022, : 248 - 254
  • [50] Virus Named Entity Recognition based on Pre-training Model
    Mou, Hanlin
    Zheng, Shanshan
    Wu, Haifang
    Li, Bojing
    He, Tingting
    Jiang, Xingpeng
    2020 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2020, : 473 - 476