Author(s)

N. Zhong, Y.Y. Yao & Y. Kakemoto

Abstract

The paper describes a multi-phase process of automatic construction of the domain specific ontology from text databases, in which various text mining and natural-language understanding methods are used. The ontology we wish to develop describes a well-defined technical domain. Hence it is called a domain specific ontology, opposed to universal ontologies. We discuss the major techniques used in the process and show some preliminary results. 1 Introduction It has been recently recognized in the KDD (Knowledge Discovery and Data Mining) community that mining from semi-structured or unstructured text (text mining for short) is an increasingly important research topic, and there are enormous potential applicatio

Keywords