Definition-based information content vectors for semantic similarity measurement

Citation

Pesaranghader, Ahmad and Muthaiyah, Saravanan (2013) Definition-based information content vectors for semantic similarity measurement. In: Soft Computing Applications and Intelligent Systems. Communications in Computer and Information Science, 378 (378). Springer Berlin Heidelberg, pp. 268-282. ISBN 978-3-642-40566-2

Full text not available from this repository.

Abstract

Ontologies, as representation of shared conceptualization for variety of specific domains, are the heart of the Semantic Web. In order to facilitate interoperability across multiple ontologies, we need an automatic mechanism to align ontologies. Therefore, many methods to measure similarity between concepts existing in two different ontologies are proposed. In this paper, we will enumerate these methods along with their shortcomings in each case. In information content (IC) based similarity measures, the process of IC computation for concepts is so challenging and in many cases with failing. We will propose our new approach that is based on concepts’ definitions. These definitions would help us to compute reliable and easy to calculate information contents for concepts. Applying these methods to the biomedical domain, using MEDLINE as corpus, International Classification of Diseases, Ninth Revision, Clinical Modification (ICD9CM) as thesaurus, and available reference standard, we will find our method outperforms other similarity measures.

Item Type: Book Section
Additional Information: Book Subtitle: Second International Multi-Conference on Artificial Intelligence Technology, M-CAIT 2013, Shah Alam, August 28-29, 2013. Proceedings
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Management (FOM)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 28 Feb 2014 02:49
Last Modified: 28 Feb 2014 02:49
URII: http://shdl.mmu.edu.my/id/eprint/5334

Downloads

Downloads per month over past year

View ItemEdit (login required)