Optimizing Ontology Alignments through NSGA-II Using an Aggregation Strategy and a Mapping Extraction Approach

Ontology which defines a common vocabulary for researchers who need to share information in a domain is brought for convenience. However, because of human subjectivity, merely using ontology may raise the heterogeneity problem to a higher level. Therefore, it is necessary for us to find out the relationships that hold between two entities from two ontologies. The process of finding these correspondences is called ontology matching and the matching results are called ontology alignment. Various ontology matching approaches have been proposed so far, but they all have their own advantages and shortcomings. Thus, several approaches used for optimizing the ontology alignments through evolutionary are born at the right moment, nevertheless, the quality of the results obtained and the efficiency of these algorithms are both barely satisfactory. To address those issues, in this paper, we propose a novel approach to apply NSGA-II to optimize ontology alignments. In our approach, a general aggregation strategy and a special mapping extraction approach are proposed. Experimental results show that our approach is efficient and can find the best solution so far.