中文信息学报中文金融新闻中公司名的识别 - PolyU IRA.PDF

　　　　　 16 2 　 JOURNAL OF CHINESE INFORMATION PROCESSING Vol.16 No.2 1 1 1 2 3 　 　 　 　 　 (1.　　　100084 2.　3.) :在金融领域信息抽取中, 公司名扮演着非常重要的角色;因此如何正确识别 本中出现的公司名是 一个非常重要的研究课题。在对金融新闻 本进行了深入地分析和研究的基础上, 总结出了公司名的结构特 征及其上下 信息, 建立了六 个用于识别公司名的知识库, 并提出了 一个基于两次扫描过程的识别策略。初 步实验结果表明,在封闭测试中实验系统公司名识别的精确率可以达到97.3%, 召回率可达89.3%;在开放 测试中精确率可以达到62.8%, 召回率可达62.1%。 :公司名;金融领域;专名识别;信息抽取 :TP391.4 Company Name Identification in C inese Financial Domain 1 1 1 2 3 WAN G N ing 　G E Rui-fang 　YU AN Chun-fa 　K.F.Wong 　L Wen-jie (1.S tate Key Laboratory of ntelligent T echnology and System Dept.of Comput er S cience T echnology 　T singhua University 　Beijing 　100084 2.Dept.of System Engineering Engineering M anagement　T he C hinese University of Hong Kong 　Hong Kong 3.Departmen t of Computing 　The Hong Kong Polytechnic University 　Hung Hom 　Hong Kong) Abstract:dentifying company names in running tex ts plays a sig nificant role in financial information ex traction. Based on the thoroughly investigations of financial articles, the relevant structural features and contextual constraints w ere obtained.n this paper, a company name identification system is proposed,which is built o n the six knowledge- bases and a twice-scan method.T he ex periment achieved 97.3%precision and 89.3% recall respectively by close test, and 62.8%precision and 62.1%recall respectively by open test. Keywords:company name;financial domain;named entity identification;information ex traction 、 (nf orm ation Ex traction, E)(M achine T ranslation, M T )(nformation Retrieval, R) [6] 。 , [5] (Named Entity,NE)、、 。