###
计算机系统应用:2018,27(9):18-24
本文二维码信息
码上扫一扫!
基于GRU的命名实体识别方法
王洁1, 张瑞东1, 吴晨生2
(1.北京工业大学 信息学部, 北京 100124;2.北京市科学技术情报研究所, 北京 100048)
Named Entity Recognition Method Based on GRU
WANG Jie1, ZHANG Rui-Dong1, WU Chen-Sheng2
(1.Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;2.Beijing Institute of Science and Technology Information, Beijing 100048, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 254次   下载 313
投稿时间:2018-01-10    修订日期:2018-01-31
中文摘要: 命名实体识别是自然语言处理中的一项基础任务,传统的识别方法往往需要外部知识和人工筛选特征,需要较高的人力成本和时间成本;针对传统方法的局限性,提出一种基于GRU (Gated Recurrent Unit)的命名实体识别模型,该模型以字向量作为输入单位,通过双向GRU层提取特征,并通过输出层得到标签序列.在传统命名实体和会议名称这种特定领域命名实体上对该模型进行了测试.实验结果表明,本文设计的循环神经网络模型能有效的识别命名实体,省去了人工设计特征的繁琐工作,提供了一种端到端的识别方法.
Abstract:Named entity recognition is a basic task of natural language processing. Traditional recognition methods often require external knowledge and manual screening features, which require high labor costs and time costs. Aiming at the limitation of traditional methods, this study proposes a named entity recognition model based on GRU (Gated Recurrent Unit). This model uses word vector as input unit, extracts features through bi-directional GRU layer, and obtains label sequence through output layer. In this study, this model has been tested on a specific domain named entity. The experimental results show that the recurrent neural network model of the article can identify the named entities well, and can save the tedious work of designing the features manually and provide the end-to-end identification method.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
王洁,张瑞东,吴晨生.基于GRU的命名实体识别方法.计算机系统应用,2018,27(9):18-24
WANG Jie,ZHANG Rui-Dong,WU Chen-Sheng.Named Entity Recognition Method Based on GRU.COMPUTER SYSTEMS APPLICATIONS,2018,27(9):18-24

用微信扫一扫

用微信扫一扫