【作者】 史树敏； 王志强； 周浪； 冯冲； 黄河燕；

【Author】 Shumin SHI, Zhiqiang WANG,Lang ZHOU,Chong FENG,Heyan HUANG (Department of Computer Science & Technology, Nanjing University of Science & Technology, Nanjing 210094; Research Center of Language & Information Engineering, CAS, Beijing 10083; Computer & Information Engineering College, Inner Mongolia Normal University, Huhhot 010022 )

【机构】 南京理工大学计算机科学与技术学院； 中国科学院计算语言信息工程研究中心；

【摘要】 本文基于条件随机域模型处理中文命名实体中的人名、地名、组织机构名识别,综合利用外部特征,研究了字一级包括外国译名在内的中文人名、地名、简单组织机构名的识别,采用了利用互信息获取外部统计词典并建立外部特征的方法。初步实验结果表明,外部特征的加入可以弥补训练规模的不足、显著提高识别效果。更多还原

【Abstract】 This paper studies the recognition of Chinese person name, including translated name, location name, simple organization name on character level using conditional random fields model (CRFs), which used to deal with Chinese named entity recognition, while utilizing external feature synthetically, adopting an approach of making use of mutual information to obtain external statistical lexicon and establishing external feature. Experiment shows that joining external feature can offset the deficiency of training models and improve the effect of recognition prominently.更多还原