A hybrid concept similarity measure model for ontology environment

Dong, H, Hussain, F and Chang, E 2009, 'A hybrid concept similarity measure model for ontology environment', Lecture Notes in Computer Science, vol. 5872, pp. 848-857.


Document type: Journal Article
Collection: Journal Articles

Title A hybrid concept similarity measure model for ontology environment
Author(s) Dong, H
Hussain, F
Chang, E
Year 2009
Journal name Lecture Notes in Computer Science
Volume number 5872
Start page 848
End page 857
Total pages 10
Publisher Springer
Abstract In this paper, we present a hybrid concept similarity measure model for the ontology environment. Whilst to date many similar technologies have been developed for semantic networks, few of them can be directly applied to the semantic-rich ontology environment. Before the measure model is adopted, an ontology is required to be converted into a lightweight ontology space, and within it all the ontology concepts need to be transformed into the pseudo-concepts. By means of this model, ontology concept similarities are measured respectively based on the content of pseudo-concepts and the structure of the lightweight ontology space. Afterwards, the two aspects of concept similarity are leveraged as the eventual product. In addition, an experiment is conducted to evaluate the measure model based on a small ontology. Conclusions are drawn and future works are planned in the final section.
Subject Information Engineering and Theory
Keyword(s) concept similarity measure
latent semantic indexing
ontology
semantic similarity models
Copyright notice © Springer-Verlag Berlin Heidelberg 2009
ISSN 0302-9743
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 4 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 7 times in Scopus Article | Citations
Access Statistics: 197 Abstract Views  -  Detailed Statistics
Created: Tue, 24 Jun 2014, 08:49:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us