基于CRF的中文命名实体识别
RFs-Based Chinese Named Entity Recognition with improved Tag Set
中文命名实体识别在自然语言处理中是一个很重要的任务。本文主要介绍我们的团队在中文命名实体识别任务方面的工作。本文建立了一个基于条件随机域（CRF）模型的系统。引入了改进标注集以后，系统获得的F 值达93.49，使用的是SIGHAN2007 MSRA语料库。
hinese Named entity recognition is one of the most important tasks in NLP. The paper mainly describes our work on NER tasks. The paper built up a system under the framework of Conditional Random Fields (CRFs) model. With an improved tag set the system gets an F-value of 93.49 using SIGHAN2007 MSRA corpus.
曾冠明、肖波、张闯、蔺志青
汉语
命名实体识别RF标注集
NERCRFtag-set
曾冠明,肖波,张闯,蔺志青.基于CRF的中文命名实体识别[EB/OL].(2009-02-05)[2025-08-02].http://www.paper.edu.cn/releasepaper/content/200902-147.点此复制
评论