2003 Volume 2003 Issue SWO-004 Pages 08-
We develop a system, which collect, extract and combine non-structured, structured and semi-structured information based on ontology. This paper explains how to construct ontology about IT domain based on web contents analysis, and describes an outline of the system developed. An information extraction process, which is one of important processes in the system, is detailed, and an experiment report on information extraction from web pages is also introduced.