| Popis: |
Ontologies are increasingly important in the Semantic Web and biomedical informationsystem fields. Ontology alignment (OA) is the process of finding semantic mappingsbetween the concepts of two given ontologies. OA systems have begun using mediatingontologies pre-selected to improve OA performance. This research investigates theautomatic selection of a set of mediating ontologies from a large set of ontologies in thebiomedical domain. BioPortal, an online library offering biomedical ontologies via webAPI and web browsing, is used as the background knowledge source. The anatomy andthe large biomedical ontologies tracks of the Ontology Alignment Evaluation Initiativeare used to evaluate this approach which is implemented as a software componentaccessed from a leading OA system LogMap. The experimental results showautomatically selected mediating ontologies improve the recall and f-measure for theanatomy track. For the large biomedical ontologies track, three of the six tasks showsome overall improvement. |
