Ontology-based knowledge extraction from hidden web

被引：0

作者：

Song, Hui ^{[1
,2
]}

Ma, Fan-Yuan ^{[2
]}

Liu, Xiao-Qiang ^{[1
]}

机构：

[1] Dept. of Comp. Sci. and Eng., Shanghai Jiaotong Univ., Shanghai 200030, China

[2] Dept. of Comp. Info. Technol., Donghua Univ., Shanghai 200052, China

来源：

Journal of Dong Hua University (English Edition) | 2004年 / 21卷 / 05期

关键词：

Algorithms - Database systems - Feature extraction - World Wide Web;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Hidden Web provides great amount of domain-specific data for constructing knowledge services. Most previous knowledge extraction researches ignore the valuable data hidden in Web database, and related works do not refer how to make extracted information available for knowledge system. This paper describes a novel approach to build a domain-specific knowledge service with the data retrieved from Hidden Web. Ontology serves to model the domain knowledge. Queries forms of different Web sites are translated into machine-understandable format, defined knowledge concepts, so that they can be accessed automatically. Also knowledge data are extracted from Web pages and organized in ontology format knowledge. The experiment proves the algorithm achieves high accuracy and the system facilitates constructing knowledge services greatly.

引用

页码：73 / 78