Using a lexical dictionary and a Folksonomy to automatically construct domain ontologies

Macias Galindo, D, Wong, W, Cavedon, L and Thangarajah, J 2011, 'Using a lexical dictionary and a Folksonomy to automatically construct domain ontologies', in Kevin Wong, Lance Fung, Hussein Abbass (ed.) 24th Australasian Joint Conference on Artificial Intelligence (AI2011), Perth, Australia, 5-8 December 2011, pp. 1-10.


Document type: Conference Paper
Collection: Conference Papers

Title Using a lexical dictionary and a Folksonomy to automatically construct domain ontologies
Author(s) Macias Galindo, D
Wong, W
Cavedon, L
Thangarajah, J
Year 2011
Conference name 24th Australasian Joint Conference on Artificial Intelligence (AI2011)
Conference location Perth, Australia
Conference dates 5-8 December 2011
Proceedings title 24th Australasian Joint Conference on Artificial Intelligence (AI2011)
Editor(s) Kevin Wong, Lance Fung, Hussein Abbass
Publisher Springer
Place of publication Berlin, Germany
Start page 1
End page 10
Total pages 10
Abstract We present and evaluate MKBUILD, a tool for creating domain-specific ontologies. These resources, which we named Modular Knowledge Bases (MKBs), feature concepts and associations imported from existing large-scale knowledge resources, in particularWordNet and Wikipedia. The combination of WordNet's human-crafted taxonomy and Wikipedia's semantic associations between articles produces a highly connected resource. MKBs are utilised by a conversational agent op-erating on a small computational environment. We constructed several domains with our technique, and then conducted an evaluation by asking human subjects to rate the relevance of the concepts included in these ontologies on a scale from 0 to 2. The proposed methodology achieved precision values between 71% and 88% and recall between 37% and 95% in the evaluation depending on the interpretation of judgements scored with 1. The results are encouraging considering the cross-domain nature of the construction process and the difficulty of representing concepts as opposed to terms.
Subjects Organisation of Information and Knowledge Resources
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 3 times in Scopus Article | Citations
Access Statistics: 190 Abstract Views  -  Detailed Statistics
Created: Fri, 09 Mar 2012, 08:22:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us