Efficient Matching for Large Real-World Schemas and Ontologies
We consider the problem of defining mappings among schema or ontology concepts that are semantically related. The solution to this matching problem is necessary for the seamless integration of heterogeneous data sources in a wide range of applications in the geospatial, environmental, and biomedical domains. A few thousand concepts can exist in the schemas or ontologies, thus requiring automatic matching techniques.
In this talk, we describe AgreementMaker, a system that incorporates a variety of matching methods. In particular, we describe two fully automatic methods that take into account the conceptual graph structure. We have validated our approach by comparing the efficiency of our methods in terms of precision, recall, and runtime against other methods. We have further confirmed the effectiveness of AgreementMaker by participating in a competition run by the Ontology Alignment Evaluation Initiative (OAEI). The system has also been tested with expert users who routinely match geospatial ontologies. Finally, we outline our work in the related subjects of privacy-preserving ontology matching and of ontology matching for the semantic desktop.
Bio Isabel F. Cruz is an Associate Professor in the Department of Computer Science, College of Engineering, at the University of Illinois at Chicago (UIC). She holds a PhD in Computer Science from the University of Toronto.
She has been invited to give more than 50 talks worldwide and has more than 80 refereed research articles in Databases, Semantic Web, Visual Languages, Graph Drawing, User Interfaces, Multimedia, Geographic Information Systems, Information Retrieval, and Security. Her research awards include a National Science Foundation CAREER Award (1996) and the UIC College of Engineering Faculty Research Award (2005). In the last ten years, she has received six teaching awards and nominations.
She has been the program committee chair or vice-chair of thirteen conferences, including recently the International Semantic Web Conference (2006) and the IEEE International Conference on Data Engineering (2009). She was a member of the National Academies Mapping Science Committee (2004-2006), has served as an editor for nineteen journals, conference proceedings, and books, and is a member of several steering committees, including that of the newly formed ACM SIGSPATIAL.
She has an extensive track record in advising and mentoring undergraduate and graduate students, postdocs and young faculty, particularly women and minorities. Since 2002, she has been the Computer Science Facilitator for WISEST (Women in Science and Engineering System Transformation), the NSF-funded ADVANCE program initiative at UIC.