面向人名消歧任务的人名识别系统

被引:4
作者
时迎超 [1 ,2 ]
王会珍 [1 ,2 ]
肖桐 [1 ,2 ]
胡明涵 [1 ,2 ]
机构
[1] 东北大学自然语言处理实验室
[2] 医学影像计算教育部重点实验室(东北大学)
关键词
人名识别; 人名消歧; 系统整合; 启发式规则;
D O I
暂无
中图分类号
TP391.1 [文字信息处理];
学科分类号
摘要
CLP2010(CIPS-SIGHAN Joint Conference on Chinese Language Processing)的人名消歧评测的任务是个聚类问题:对给定的一组文档,按照文档中出现的指定查询词所指向的人进行聚类。由于是用"字"串匹配的方法从新华社的语料库中抽出所有含有该查询词的文档。所以对于这个任务,首要问题是判定查询词是否是人名,是完整人名还是人名的一部分。为此该文实现了一个基于多实体识别系统整合和启发式规则的后处理方法的人名识别系统,从而实现对文档中的人名,特别是查询词所涉及的人名的识别。在CLP2010的评测方给的训练集上的实验表明,查询词涉及的人名的识别正确率达到98.89%。
引用
收藏
页码:17 / 22
页数:6
相关论文
共 8 条
[1]  
Description of the NetOwlTM extractor system as used for MUC-7. Krupka G R,Hausman K. Proceedings of MUC-7 . 1998
[2]  
Chineseword segmentation and named entity recognition based onconditional random fields. Mao Xinnian,Dong Yuan,He Saike,et al. IJCNLP 2008 . 2008
[3]  
CRFs-Based Named EntityRecognition Incorporated with Heuristic Entity ListSearching. Yang F,Zhao J,Zou B. Sixth SIGHAN Workshop on ChineseLanguage Processing . 2008
[4]  
Using N-best Lists for Named Entity Recognition from Chinese Speech. Zhai L,,FUNG P,SCHWARTZ R et al. Proceedings of HLT/NAACL-2004 . 2004
[5]  
Detecting Semantic Relations betweenNamed Entities in Text Using Contextual Features. Hirano T. Proceedings of the 45th Annual Meeting of theAssociation for Computational Linguistics . 2007
[6]  
Chinese NER Using CRFs and Logic for the Fourth SIGHAN Bakeoff. X. Yu,,W. Lam,,S. Chan,,Y. Wu,,B. Chen. Sixth SIGHAN Workshop on Chinese Language Processing . January11-122008
[7]  
Description of the MENE Named Entity System as Used in MUC-7. Borthwick A,Sterling J,Agichtein E et al. Proceedings of the 7th Message Understanding Conference(MUC-7) . 1998
[8]  
Description of the NE System Used for MUC-7. W.J.Black,F.Rinaldi,D.Mowatt. Proceedings of 7thMessage Understanding Conference(MUC-7) . 1998