ILIADS: Leveraging data and structure in ontology integration

Jump to:


Project Description

There is a great deal of research on ontology integration which makes use of rich logical constraints to reason about the structural and logical alignment of ontologies. There is also considerable work on matching data instances from heterogeneous schema or ontologies. However, little work exploits the fact that ontologies include both data and struc ture. We aim to close this gap by presenting a new algorithm (ILIADS) that tightly integrates both data matching and logical reasoning to achieve better matching of ontologies. We evaluate our algorithm on a set of 30 pairs of OWL Lite ontologies with the schema and data matchings found by human reviewers. We compare against two systems - the ontology matching tool FCA-merge and the schema
matching tool COMA++. ILIADS shows an average improvement of 25% in quality over FCA-merge and a 11% improvement in recall over COMA++.

To better understand how ontology alignment algorithms behave, we have developed HOMER, a GUI for ontology visualization and analysis. HOMER grants the user fine-grained control of the alignment algorithm, displaying its decision step-by-step and allowing the user to override them. Furthermore, one can also compare different instances of the same algorithm (with different parameters) or separate algorithms.

This work was supported by the National Science Foundation, NSF #0438866



Lise Getoor, Assistant Professor, Computer Science / UMIACS
Renée J. Miller, Professor, University of Toronto


Octavian Udrea, PhD Student, Computer Science / UMIACS  


     HOMER: Ontology visualization and analysis
       Octavian Udrea, Renée J. Miller and Lise Getoor
       Demo presentation at ISWC 2007
       [PDF] [Poster] [Short demo ]
     Leveraging data and structure in ontology integration
       Octavian Udrea, Renée J. Miller and Lise Getoor
       Proceedings of SIGMOD 2007
       [PDF] [Slides]
   Combining statistical and logical inference for ontology alignment
       Octavian Udrea and Lise Getoor
       IJCAI-07 workshop on Semantic Web for Collaborative Knowledge Acquisition


Please send any suggestions, comments and/or bug reports to udrea at umiacs dot umd dot edu.


Dataset(Updated 7/19/08!): [Ontologies] (27MB)


Last Updated: 06/23/2008