Matching ontologies which utilize significantly heterogeneous terminologies is a challenging task for existing matching techniques. These techniques typically exploit lexical resources in order to enrich the ontologies with additional terminology such that more terminological matches can be found. However, they are limited by the availability of an appropriate lexical resource for each matching task. For this scenario, we propose a new technique exploiting partial alignments. We evaluate our technique on a dataset which is characterized by matching problems with significant terminological heterogeneities. Further, we compare our technique with the performance of matching systems utilizing lexical resources to establish whether a partial-alignment-based matcher can perform similarly to a lexical-based matcher. Lastly, we provide a performance indication of a system utilizing both partial alignments and lexical resources.
Schadd, F. C., & Roos, N. (2015). Matching Terminological Heterogeneous Ontologies by Exploiting Partial Alignments. SEMAPRO 2015, The Ninth International Conference on Advances in Semantic Processing, 13–18. Retrieved from https://www.thinkmind.org/index.php?view=article&articleid=semapro_2015_1_30_30023