Most ontology learning tools concentrate on extracting concepts and instances from text corpora. There are some recent tools that employ linguistics or data mining to uncover concept relationships, but the results are mixed. Since relationships are semantically complex notions, it seems interesting to combine approaches that address different aspects of concept relationships. In this paper we present a hybrid approach that combines the co-occurrence principle from association rules with contextual similarities from linguistics. The technique has been tested in an ontology engineering project, and the results show significant improvements over traditional techniques.
展开▼
