Gajderowicz_Bart.pdf (2.94 MB)
Using decision trees for inductively driven semantic integration and ontology matching
thesis
posted on 2021-05-23, 15:48 authored by Bart GajderowiczThe popularity of ontologies for representing the semantics behind many real-world domains has created a growing pool of ontologies on various topics. While different ontologists, experts, and organizations create the vast majority of ontologies, often for internal use of for use in a narrow context, their domains frequently overlap in a wider context, specifically for complementary domains. To assist in the reuse of ontologies, this thesis proposes a bottom-up technique for creating concept anchors that are used for ontology matching. Anchors are ontology concepts that have been matched to concepts in an eternal ontology. The matching process is based on inductively derived decision trees rules for an ontology that are compared with rules derived for external ontologies. The matching algorithm is intended to match taxomonies, ontologies which define subsumption relations between concepts, with an associated database used to derive the decision trees. This thesis also introduces several algorithm evolution measures, and presents a set of use cases that demonstrate the strengths and weaknesses of the matching process.
History
Language
engDegree
- Master of Science
Program
- Computer Science
Granting Institution
Ryerson UniversityLAC Thesis Type
- Thesis