A Semantic-based Concept Clustering Mechanism for Chinese News Ontology Construction

Abstract

In order to efficiently manage and use knowledge, the technologies of ontology are widely applied to various kinds of domain knowledge. This paper proposes an automatic concept construction approach that can help knowledge manager efficiently construct a Chinese News domain knowledge. The first feature of this paper is to utilize an object-oriented approach to represent the structure of ontology, called object-oriented ontology. Second, the automatic ontology construction approach for Chinese News domain is presented. We embed CKIP system to carry out the Chinese natural language processing including part-of-speech tagging, Chinese-Term analysis and Chinese-Term feature selection. Third, the concept clustering mechanisms for Chinese News domain ontology construction based on fuzzy compatibility relation approach are proposed. Furthermore, the parallel fuzzy inference mechanism is also adopted to infer the conceptual resonance strength of any two Chinese terms. By the simulation, the proposed mechanism can efficiently cluster the semantic concept for Chinese News ontology construction.