Extracting Relations from Chinese Web Documents Using Kernel Methods

Author

Qiu, Jing ; Liao, Lejian

Author_Institution

Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China

fYear

2009

fDate

1-3 June 2009

Firstpage

352

Lastpage

356

Abstract

Extracting instances of a given target relation from a given Web page corpus seems to be the basic work to exploit nearly endless source of knowledge which provided by the World Wide Web. In this paper, we present an automated system which could extract instances of an arbitrary given binary relation from Chinese Web documents in domain of football games. Different syntactic sources are combined by Kernel methods. And dependency path is used as pattern information when discover relation pairs. Moreover, composite kernels are developed to show the usefulness of different syntactic sources. Experimental results show the effectiveness and benefits of our approach.

Keywords

Internet; document handling; game theory; knowledge acquisition; operating system kernels; Chinese Web document; Web page; World Wide Web; football game; kernel method; syntactic source; Computer science; Convolution; Data mining; Information science; Information technology; Kernel; Laboratories; Support vector machines; Web pages; World Wide Web; Relation extraction; composite kernels; machine learning; syntactic kernels;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Science, 2009. ICIS 2009. Eighth IEEE/ACIS International Conference on

Conference_Location

Shanghai

Print_ISBN

978-0-7695-3641-5

Type

conf

DOI

10.1109/ICIS.2009.43

Filename

5222896