基于深度学习的中文命名实体识别最新研究进展综述  

Recent Advances of Chinese Named Entity Recognition Based on Deep Learning

作　　者：张汝佳 代璐 王邦 郭鹏 ZHANG Rujia;DAI Lu;WANG Bang;GUO Peng(School of Electronic Information and Communications,Huazhong University of Science andTechnology,Wuhan,Hubei 430074,China)

机构地区：[1]华中科技大学电子信息与通信学院,湖北武汉430074

出　　处：《中文信息学报》2022年第6期20-35,共16页Journal of Chinese Information Processing

基　　金：国家自然科学基金(62172167)。

摘　　要：中文命名实体识别(CNER)任务是问答系统、机器翻译、信息抽取等自然语言应用的基础底层任务。传统的CNER系统借助人工设计的领域词典和语法规则,取得了不错的实验效果,但存在泛化能力弱、鲁棒性差、维护难等缺点。近年来兴起的深度学习技术通过端到端的方式自动提取文本特征,弥补了上述不足。该文对基于深度学习的中文命名实体识别任务最新研究进展进行了综述,先介绍中文命名实体识别任务的概念、应用现状和难点,接着简要介绍中文命名实体识别任务的常用数据集和评估方法,并按照主要网络架构对中文命名实体识别任务上的深度学习模型进行分类和梳理,最后对这一任务的未来研究方向进行了展望。Chinese named entity recognition(CNER)is one of the basic tasks of natural language processing applications such as question answering systems,machine translation and information extraction.Although traditional CNER system has achieved satisfactory experiment results with the help of manually designed domain-specific features and grammatical rules,it is still defected in aspects such as weak generalization ability,poor robustness and difficult maintenance.In recent years,deep learning techniques have been adopted to deal with the above shortcomings by automatically extracting text features in an end-to-end learning manner.This article surveys the recent advances of deep learning-based CNER.It first introduces the concepts,difficulties and applications of CNER,and introduces the common datasets and evaluation metrics.Recent neural network models for the CNER task are then grouped according to their network architectures,and representative models in each group are detailed.Finally,future research directions are discussed.

关 键 词：中文命名实体识别 深度学习 综述 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]