Continual Word Embedding Based for Matching Lightweight Ontologies

Ontology matching is the task of finding alignments between two different ontologies. It has become the key point of building knowledge base and integrating heterogeneous data. In this paper, a novel ontology matching approach that is based on continual word embedding is proposed. We describe in details how is skip-gram model adapted to capture the semantic of words to learn the word embedding. After computing the name similarity of concepts, similarity flooding algorithm is used to fix the initial similarity. Experiments on Ontology Alignment Evaluation Initiative (OAEI) benchmark without instances show that the proposed method significantly improves the quality of mappings.