Multi-Feature Fusion Transformer for Chinese Named Entity Recognition

被引:0
|
作者
Han, Xiaokai [1 ]
Yue, Qi [1 ]
Chu, Jing [1 ]
Han, Zhan [1 ]
Shi, Yifan [1 ]
Wang, Chengfeng [1 ]
机构
[1] Xian Univ Posts & Telecommun, Sch Automat, Xian, Peoples R China
关键词
Multi feature; Radical; Semantic enhancements; Transformer; Chinese named entity recognition;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, an approach to enhancing semantic and entity boundaries through lexicons has been used in Chinese named entity recognition tasks to improve recognition rate. However, this approach ignores the radicals of Chinese characters. As a kind of characters that evolve from pictographs, a lot of information is embedded in the radicals of Chinese characters. This paper proposes a novel Chinese named entity recognition method, named Multi-feature Fusion Transformer (MFT), which exploits the information of the radicals of Chinese characters. Our model is able to further enhance the semantic information by adding the radical information of Chinese characters while using word features. We have also improved the basic structure of the Transformer model to make the model perform better in entity recognition. Our model is compared with other mainstream models on Resume dataset and Weibo dataset, the experimental results show that our model is significantly better than other models, with F1 score of 95.77% and 64.38% for the respective dataset.
引用
收藏
页码:4227 / 4232
页数:6
相关论文
共 50 条
  • [41] Chinese named entity recognition with multi-network fusion of multi-scale lexical information
    Yan Guo
    HongChen Liu
    FuJiang Liu
    WeiHua Lin
    QuanSen Shao
    JunShun Su
    Journal of Electronic Science and Technology, 2024, 22 (04) : 55 - 82
  • [42] Citation entity recognition method using multi-feature semantic fusion based on deep learning
    Gao, Jie
    Zhang, Zuping
    Cao, Ping
    Huang, Wei
    Li, Fangfang
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2022, 34 (06):
  • [43] Joint entity and relation extraction with fusion of multi-feature semantics
    Wang, Ting
    Yang, Wenjie
    Wu, Tao
    Yang, Chuan
    Liang, Jiaying
    Wang, Hongyang
    Li, Jia
    Xiang, Dong
    Zhou, Zheng
    JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2024, : 21 - 42
  • [44] EEG FEATURE EXTRACTION AND RECOGNITION BASED ON MULTI-FEATURE FUSION
    Sun, Jian
    Wu, Quanyu
    Gao, Nan
    Pan, Lingjiao
    Tao, Weige
    BIOMEDICAL ENGINEERING-APPLICATIONS BASIS COMMUNICATIONS, 2024, 36 (06):
  • [45] Multi-Feature Fusion Event Argument Entity Recognition Method for Industrial Robot Fault Diagnosis
    Chen, Senye
    Cheng, Lianglun
    Deng, Jianfeng
    Wang, Tao
    APPLIED SCIENCES-BASEL, 2022, 12 (23):
  • [46] Multi-Strategy Fusion for Medical Named Entity Recognition
    Sun, Jian
    Tang, RongChuan
    Xiang, Lu
    Zhai, FeiFei
    Zhou, Yu
    2021 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING (IALP), 2021, : 117 - 120
  • [47] MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition
    Wu, Shuang
    Song, Xiaoning
    Feng, Zhenhua
    59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 1529 - 1539
  • [48] Human action recognition using multi-feature fusion
    Shao, Yan-Hua, 1818, Board of Optronics Lasers (25):
  • [49] Robust Chinese Named Entity Recognition Based on Fusion Graph Embedding
    Song, Xuhui
    Yu, Hongtao
    Li, Shaomei
    Wang, Huansha
    ELECTRONICS, 2023, 12 (03)
  • [50] Chinese named entity recognition method based on Transformer and hidden Markov model
    Li J.
    Xiong Q.
    Hu Y.-T.
    Liu K.-Y.
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2023, 53 (05): : 1427 - 1434