Compound Concept Semantic Similarity Calculation Based on Ontology and Concept Constitution Features

The computation of semantic similarity between words is important in information retrieval, knowledge acquisition and many other fields. The existing studies are mainly aiming at single concepts composed of single terms. For the compound concepts composed of multiple terms, they usually neglect the special constitution features of compounds and only process them as single concepts, which may affect the ultimate accuracy. In this paper, we propose a novel ontology-based Compound Concept Semantic Similarity calculation approach called CCSS which exploits concept constitution features. In CCSS, the compound is decomposed into Subject headings and Auxiliary words (SaA), and the relationships between these two sets are used to measure the similarity. Besides, the errors that may be caused by SaA recognition are corrected. Moreover, several information sources of ontology such as taxonomical features, local density and depth are considered. Extensive experimental evaluations demonstrate that our approach significantly outperforms existing approaches.