GlossOnt: A Concept-focused Ontology Building Tool

Abstract

The demand for ontologies is rapidly growing especially due to developments in knowledge management, E-commerce and the Semantic Web. Building an ontology and a background knowledge base manually is so costly and time-consuming that it hampers progress in intelligent information access. Therefore, semi-automatic or automatic construction of ontologies is very useful. This paper presents a concept-focused ontology building method based on text mining technology. The method focuses on a particular domain concept at a time and actively acquires source documents for the ontological knowledge about the concepts. It begins with the analysis of glossary definitions about the target concept by extracting classes and relationships. Then, it generates advanced queries from the result of glossary definition processing and activates a Web search engine to obtain more documents relevant to the target concept. The method extends the ontological knowledge by extracting more domain-specific concepts and relationships from the search documents. By focusing on a specific concept and highly relevant document set, this method suffers less ambiguity and can identify domain concepts and relations more accurately. In addition, by acquiring source documents from the Web on demand, the method can produce up-to-date ontologies.