Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (19): 52-65.DOI: 10.3778/j.issn.1002-8331.2211-0423

• Research Hotspots and Reviews • Previous Articles     Next Articles

Study of Named Entity Recognition Based on Graph Neural Network

SHU Wenhao, XI Xuefeng, CUI Zhiming, GU Chenkai   

  1. 1.School of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215000, China
    2.Suzhou Key Laboratory of Virtual Reality Intelligent Interaction and Application Technology, Suzhou, Jiangsu 215000, China
    3.Suzhou Smart City Research Institute, Suzhou, Jiangsu 215000, China
  • Online:2023-10-01 Published:2023-10-01



  1. 1.苏州科技大学 电子与信息工程学院,江苏 苏州 215000
    2.苏州市虚拟现实智能交互及应用技术重点实验室,江苏 苏州 215000
    3.苏州智慧城市研究院,江苏 苏州 215000

Abstract: Named entity recognition is one of the pre-processing tasks in natural language processing, aiming at identifying desired entities and types from unstructured text, and is used in many downstream tasks, such as building knowledge graphs, event extraction and automatic question and answer. In recent years, with the wide application of graph neural networks in the field of natural language processing, some graph neural network-based named entity recognition methods have achieved good results. This paper systematically investigates the application of graph neural networks in named entity recognition, firstly, describes the development process of named entity recognition, secondly, introduces graph neural networks and three variant models, then details how to use the features of graph neural networks for named entity recognition tasks, and finally, this paper proposes possible directions and ideas for future research and summarizes them.

Key words: named entity recognition, graph neural network, natural language processing, deep learning

摘要: 命名实体识别是自然语言处理的预处理任务之一,目的是从非结构化文本中识别出所需的实体及类型,应用于众多下游任务,例如构建知识图谱、事件抽取及自动问答等。近几年,随着自然语言处理领域对图神经网络的广泛应用,一些基于图神经网络的命名实体识别方法取得了较好的结果。对图神经网络在命名实体识别中的应用进行了系统性的调研,描述了命名实体识别的发展进程,介绍了图神经网络及三种变体模型,详细分析了如何利用图神经网络的特点在命名实体识别任务上的应用研究,最后提出了未来可能研究的方向和思路。

关键词: 命名实体识别, 图神经网络, 自然语言处理, 深度学习