UMBC ebiquity

Mining Domain Specific Texts and Glossaries to Evaluate and Enrich Domain Ontologies

Authors: Viral Parekh, Jin-Ping (Jack) Gwo

Book Title: International Conference of Information and Knowledge Engineering

Date: June 21, 2004

Abstract: Ontologies have been widely accepted as the most advanced knowledge representation model. They are among the most important building blocks of semantic web, hence, very crucial for the success of semantic web. This paper discusses a fast and efficient method to facilitate the evaluation and enrichment of domain ontologies using a text-mining approach. We exploit domain specific texts and glossaries or dictionaries in order to automatically generate g-groups and f-groups. These groups are sets of concepts/terms which have either taxonomic or non-taxonomic relationships among them. The domain expert ontology engineer reviews these generated groups and uses them to evaluate and enrich the domain ontology. We have developed an extensive and detailed ontology in the field of environmental science using this approach in interaction with domain expert. Empirical results show that our approach can support domain expert ontology engineers in building domain specific ontologies efficiently.

Type: InProceedings

Address: Las Vegas, NV

Organization: The International MultiConference in Computer Science and Computer Engineering

Tags: ontology, text mining, semantic web, learning

Google Scholar: UVqm2Ei31_gJ

Number of Google Scholar citations: 24 [show citations]

Number of downloads: 7289


Available for download as

size: 116682 bytes

Related Projects:

Past Project

 Text Mining Approach to Ontology Enrichment.