Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.328
Though current ontology construction methods can achieve automated classification framework, there are limitations such as the requirement for human labor and domain restrictions. In order to overcome the problems, this paper proposes a novel method consisting of Projective Adaptive Resonance Theory (PART) neural network and Bayesian Network probability theorem to automatically construct ontology. Additionally, the system utilizes WordNet combined with TF-IDF and Entropy theorem to acquire key terms automatically. Finally, the system uses Bayesian Networks to reason out the complete hierarchy of terms and to construct the final domain ontology. The system then stores the resultant ontology using a Resource Description Framework (RDF). RDF is recommended by W3C and can deal with the lack of standard to reuse or integrate existing ontology. The experimental results indicate that this method has great promise.
domain ontology, bayesian network, ART, PART
Z. Rui-ling and X. Hong-sheng, "Using Bayesian Network and Neural Network Constructing Domain Ontology," 2009 WRI World Congress on Computer Science and Information Engineering, CSIE(CSIE), Los Angeles, CA, 2009, pp. 116-120.