Display Full Text | Download Full Text
1.06 MB PDF file

Degree

Master of Computer Science, Miami University, Computer Science, 2012.

Abstract

Measuring the similarity between concepts in two different ontologies can be done in many different ways as evidenced by the numerous kinds of matchers found in ontology alignment (OA) systems. Some produce a mapping between two concepts in different ontologies by finding an identical bridge concept in a reference ontology to which both concepts are mapped. A new matcher incorporating semantic similarity measurement within one or more reference ontologies has been integrated into the AgreementMaker OA system. Experiments using the Ontology Alignment Evaluation Initiative (OAEI) anatomy track are performed with both the Uberon and the FMA ontologies as reference ontologies. The results of these experiments are compared to the OAEI 2011 and the 2012 results for the anatomy track and show this approach performs better than most other OA systems in the OAEI competition. This thesis demonstrates that using semantic similarity measures within a reference ontology can improve the ontology alignment process.

Subject Headings

Computer Science

Keywords

ontology alignment; reference ontologies; semantic similarity

Committee / Advisors

Valerie Cross (Advisor)
Michael Zmuda (Committee Member)
James Kiper (Committee Member)

Pages

33p.

Document number: miami1356064279
Permalink: http://rave.ohiolink.edu/etdc/view?acc_num=miami1356064279

This ETD has been downloaded 28 times (through March 2013)