Ontology Matching Tuning Based on Particle Swarm Optimization: Preliminary Results

An ontology matching system can usually be run with different configurations to optimize the system’s performance, namely precision, recall, or F-measure, depending on the given ontologies to be matched. Changing the configuration has potentially high impact on the obtained matching results. This paper applies particle swarm optimization to automatically tune these configuration parameters through proactively sampling the parameters space and find high-impact parameters and high-performance parameter settings. We show the effectiveness and efficiency of our approach through extensive evaluation on the OAEI 2009 tasks using Lily ontology matching system.