Semantic-enhanced graph neural network for named entity recognition in ancient Chinese books

被引:0
作者
Xu, Yongrui [1 ]
Mao, Caixia [2 ]
Wang, Zhiyong [1 ]
Jin, Guonian [1 ]
Zhong, Liangji [1 ]
Qian, Tao [1 ]
机构
[1] Hubei Univ Sci & Technol, Sch Comp Sci & Technol, Xianning 437100, Peoples R China
[2] Hubei Univ Sci & Technol, Sch Elect & Informat Engn, Xianning 437100, Peoples R China
来源
SCIENTIFIC REPORTS | 2024年 / 14卷 / 01期
基金
中国国家自然科学基金; 国家教育部科学基金资助;
关键词
Named entity recognition; Graph neural network; Ancient Chinese; Graph attention mechanism;
D O I
10.1038/s41598-024-68561-x
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Named entity recognition (NER) plays a crucial role in the extraction and utilization of knowledge of ancient Chinese books. However, the challenges of ancient Chinese NER not only originate from linguistic features such as the use of single characters and short sentences but are also exacerbated by the scarcity of training data. These factors together limit the capability of deep learning models, like BERT-CRF, in capturing the semantic representation of ancient Chinese characters. In this paper, we explore the semantic enhancement of NER in ancient Chinese books through the utilization of external knowledge. We propose a novel model based on Graph Neural Networks that integrates two different forms of external knowledge: dictionary-level and chapter-level information. Through the Graph Attention Mechanism (GAT), these external knowledge are effectively incorporated into the model's input context. Our model is evaluated on the C_CLUE dataset, showing an improvement of 3.82% over the baseline BAC-CRF model. It also achieves the best score compared to several state-of-the-art dictionary-augmented models.
引用
收藏
页数:12
相关论文
共 37 条
[31]  
Wu S, 2022, Arxiv, DOI [arXiv:2205.05832, 10.48550/arXiv.2205.05832, DOI 10.48550/ARXIV.2205.05832]
[32]  
[徐晨飞 Xu Chenfei], 2020, [数据分析与知识发现, Data Analysis and Knowledge Discovery], V4, P86
[33]  
Yan H, 2019, Arxiv, DOI [arXiv:1911.04474, DOI 10.48550/ARXIV.1911.04474]
[34]  
Zhang W., 2022, Acad. J. Sci. Technol, V4, P97, DOI [10.54097/ajst.v4i2.3978, DOI 10.54097/AJST.V4I2.3978]
[35]   Lattice LSTM for Chinese Sentence Representation [J].
Zhang, Yue ;
Wang, Yile ;
Yang, Jie .
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2020, 28 :1506-1519
[36]  
Zhang Y, 2018, PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, P1554
[37]   Improving Chinese Named Entity Recognition by Large-Scale Syntactic Dependency Graph [J].
Zhu, Peng ;
Cheng, Dawei ;
Yang, Fangzhou ;
Luo, Yifeng ;
Huang, Dingjiang ;
Qian, Weining ;
Zhou, Aoying .
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 30 :979-991