ADVIS Lab: the AgreementMaker ontology matching system ranks high among peers
The
Ontology Alignment Evaluation Initiative (OAEI) aims to improve the work on
ontology alignment (or
matching), which is fundamental for
semantic data integration. Every year since 2004, a competition organized by OAEI takes place where state of the art ontology matching systems compete. The systems are compared in terms of precision, recall, and F-measure.
The
ADVIS Lab directed by
Professor Isabel Cruz decided to take on the challenge and participated this year with the
AgreementMaker system for ontology matching. The team also included Flavio Palandri Antonelli (MS student), Cosmin Stroe (undergraduate student), Ulas Keles (PhD student), and Angela Maduko (postdoc). AgreementMaker incorporates several matching methods (including a method that uses knowledge in the biomedical domain) and places significant emphasis on the evaluation of the quality of the obtained alignments.
AgreementMaker ranked
second among ten systems in the anatomy track whose objective is to find mappings between the ontologies describing the mouse adult anatomy published by the Mouse Gene Expression Database Project (2744 classes) and the human anatomy published by the National Cancer Institute (3304 classes). In addition to this remarkable performance, AgreementMaker was
first in the number of detected non-trivial correspondences.
AgreementMaker also participated successfully in two other tracks: benchmarks and conference. In the former track, AgreementMaker was ranked
first in terms of precision and
seventh in terms of recall among thirteen systems and in the latter track AgreementMaker was ranked
first with the highest F-measure (57%) at a threshold of 75% among seven competing systems.
This work has been sponsored by the National Science Foundation under Awards ITR IIS-0326284, IIS-0513553, and
IIS-0812258. Work on AgreementMaker can be found in the
publications page of the ADVIS Lab.
-- Main.ifcruz - 14 Oct 2009