PhD Seminar – Hlomani Hlomani
The School of Computer Science is pleased to announce the following seminar, Multidimensional Data-Driven Ontology Evaluation, presented by PhD Candidate Hlomani Hlomani. The seminar will take place April 24, 2014 in Reynolds 219 at 1:00 pm.
Multidimensional Data-Driven Ontology Evaluation
The web we experience today is in fact a fusion of two "webs"; the hypertext web that we are traditionally accustomed to also known as the web of documents and the semantic web also known as the web of data. The latter is an extension of the former. It does so by allowing the definition of semantics that enable the exchange and integration of data in communications that takes place over the web and within systems. These semantics are defined through ontologies rendering them the centrepiece for knowledge description and creation of a shared knowledge base. As a result of the important role ontologies play on the semantic web, they have seen increased research interest from both academic and industrial domains. This has lead to the proliferation of ontologies in existence which can be a double-edged sword, so to speak. Critical mass is essential for the semantic web to take off, however, in the context of reuse deciding on which ontology to use presents a big challenge. To that end a varied number of approaches to ontology evaluation have been proposed. This thesis focuses on data-driven ontology evaluation, a subset of ontology evaluation that considers knowledge about the domain to evaluate ontologies. By definition an ontology is a shared conceptualization of a domain of discourse. A conflicting factor is that, while it is a shared knowledge base, it is also created on a specific environmental setting, time, and largely based on the modeller's perception of the domain. Moreover, domain knowledge from which it is based is non-static and changes over different dimensions. These are notions that have been overlooked in current research on data-driven ontology evaluation. The ultimate goal is to answer the question: "How do the domain knowledge dimensions affect the results of data-driven ontology evaluation? Consequently, the thesis presents a theoretical framework as well as two metrics that account for bias along the dimensions of domain knowledge. To prove and demonstrate the merits of the proposed framework and metrics an experimental procedure that encompasses statistical evaluations is presented in the context of four ontologies in the workflow domain. At the most part the results of the statistical experimentation and evaluation are in support of the hypotheses of this thesis. There are, however, cases where the null hypotheses have been accepted and the alternate rejected. Direct contribution to the body of knowledge are the two metrics (date bias and category bias) to account for bias in data-driven ontology evaluation, the theoretical framework as well as the evaluation methodology. The framework and methodology can serve as a tool in the form of template upon which other dimensions can be defined and accounted for. This is a tool that can be used in the initial (pre-development), during and at post-development of ontologies to evaluate an ontology both for its coverage of the domain across the dimension of the domain and offering a comparison of the ontology's coverage of the domain for each dimension to that of the other ontologies in the same domain.
Advisor: Deborah Stacey