Apply Object-Oriented Technology to Construct Chinese News Ontology on the Internet

Abstract

The Ontology is increasingly important for many information systems and Semantic Web, while the cost of constructing ontology is too much. In this paper, we propose an automatic approach for ontology construction to assist the knowledge engineers to construct the specific domain ontology from the documents, which are gathered from Internet. We hope to raise the automation level to make correctly and efficiently build the ontology while applying the method to different domains. For different domains, we propose an approach to extract new Chinese terms from the specific corpus automatically. And we use information retrieval, natural language processing, and soft computing techniques to find out the concepts of the ontology. In addition, we extend the concept of episode to construct an Episode Net. Using Episode Net, we can find out the static attributes, dynamic operations, and the associations between concepts of the ontology. Finally, we use object-oriented model to represent the ontology and then construct the ontology with four-layer object-oriented structure. The experimental results show that our approach can effectively assist ontology engineers to construct the domain ontology.