A New Approach for Combining the Similarity Values in Ontology Alignment

Abstract

Abstract. Ontology Alignment is the process of identifying semantic correspondences between their entities. It is proposed to enable semantic interoperability between various knowledge sources that are distributed and heterogeneous. Most existing ontology alignment systems are based on the calculation of similarities and often proceed by their combination. The work presented in this paper consists of an approach denoted PBW (Precision Based Weighting) which estimates the weights to assign to matchers for aggregation. This approach proposes to measure the confidence accorded to a matcher by estimating its precision. The experimental study that we have carried out has been conducted on the Conference 1 track of the evaluation campaign OAEI 2 2012. We have compared our approach with two methods considered as the most performed in recent years, namely those based on the concepts harmony and local confidence trust respectively. The results show the good performance of our approach. Indeed, it is better in terms of precision, than existing methods with which it has been compared.

Using NSGA‐III for optimising biomedical ontology alignment

“…For a given matching scenario, YAM++ [20] evaluates the degree of reliability of these similarity measures and assigns appropriate weight values to them. More recently, Benaissa and Khiat [21] propose a heuristic strategy to estimate the weights for different similarity measures, which is of a statistical nature and estimates the weights by an estimation of the precision standard metric. Particularly, the similarity measures they use are the linguistic‐based similarity measure and structure‐based similarity measure.…”