IncMap: A Journey towards Ontology-based Data Integration

Abstract

Ontology-based data integration (OBDI) allows users to federate over heterogeneous data sources using a semantic rich conceptual data model. An important challenge in ODBI is the curation of mappings between the data sources and the global ontology. In the last years, we have built IncMap, a system to semi-automatically create mappings between relational data sources and a global ontology. IncMap has since been put into practice, both for academic and in industrial applications. Based on the experience of the last years, we have extended the original version of IncMap in several dimensions to enhance the mapping quality: (1) IncMap can detect and leverage semantic-rich patterns in the relational data sources such as inheritance for the mapping creation. (2) IncMap is able to leverage reasoning rules in the ontology to overcome structural differences from the relational data sources. (3) IncMap now includes a fully automatic mode that is often necessary to bootstrap mappings for a new data source. Our experimental evaluation shows that the new version of IncMap outperforms its previous version as well as other state-of-the-art systems.