Gold Standard Evaluation of Ontology Learning Methods Through Ontology Transformation and Alignment
Ilias Zavitsanos, George Paliouras and George Vouros
This paper presents a method along with a set of measures for evaluating learned ontologies against gold standard ontologies. The proposed method transforms the ontology concepts and their properties into a vector space representation to avoid the common string matching of concepts and properties at the lexical layer. The proposed evaluation measures exploit the vector space representation and calculate the similarity of the two ontologies (learned and gold). We provide extensive evaluation experiments which show that these measures capture accurately the deviation of the learned ontology. The proposed method is tested using the Genia and the Lonely Planet gold standard ontologies, as well as with the benchmark series of the Ontology Alignment Evaluation Initiative.