Abstract
Ontology matching is a crucial issue in the domain of semantic web and data interoperability. In this paper, a core word based method for measuring similarity from the semantic level of ontology entities is described. In ontology, most labels of entities are compound words rather than single meaningful words. However, the main meaning is represented usually by one word of them, which is called core word. The core word is learned by investigating certain patterns, which are defined based on part of speech (POS) and linguistics knowledge. The other information is noted as complementary information. An algorithm is given to measure the similarity between a pair of compound words and short texts. In order to support diverse situation, especially when core words cannot be recognized, non semantic based ontology matching techniques are applied from lexical and structural level of ontology. The described method is tested on real ontology and benchmarking data sets. It showed good matching ability and obtained promising results.