This paper introduces WikiOnto: a system that assists in the extraction and modeling of topic ontologies in a semi-automatic manner using a preprocessed document corpus derived from Wikipedia. Based on the Wikipedia XML Corpus, we present a three-tiered framework for extracting topic ontologies in quick time and a modeling environment to refine these ontologies. Using natural language processing (NLP) and other machine learning (ML) techniques along with a very rich document corpus, this system proposes a solution to a task that is generally considered extremely cumbersome. The initial results of the prototype suggest strong potential of the system to become highly successful in ontology extraction and modeling and also inspire further research on extracting ontologies from other semi-structured document corpora as well.

@inproceedings{5273871, author = {Silva, L. De and Jayaratne, L.}, title = {Semi-automatic extraction and modeling of ontologies using Wikipedia XML Corpus}, booktitle = {Applications of Digital Information and Web Technologies, 2009. ICADIWT '09. Second International Conference on the}, year = {2009}, pages = {446-451}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5273826&arnumber=5273871&count=156&index=116}, doi = {10.1109/ICADIWT.2009.5273871}, keywords = {learning, nlp, ol, ontology, wikipedia}, abstract = {This paper introduces WikiOnto: a system that assists in the extraction and modeling of topic ontologies in a semi-automatic manner using a preprocessed document corpus derived from Wikipedia. Based on the Wikipedia XML Corpus, we present a three-tiered framework for extracting topic ontologies in quick time and a modeling environment to refine these ontologies. Using natural language processing (NLP) and other machine learning (ML) techniques along with a very rich document corpus, this system proposes a solution to a task that is generally considered extremely cumbersome. The initial results of the prototype suggest strong potential of the system to become highly successful in ontology extraction and modeling and also inspire further research on extracting ontologies from other semi-structured document corpora as well.} }

%0 = inproceedings %A = Silva, L. De and Jayaratne, L. %B = Applications of Digital Information and Web Technologies, 2009. ICADIWT '09. Second International Conference on the %D = 2009 %T = Semi-automatic extraction and modeling of ontologies using Wikipedia XML Corpus %U = http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5273826&arnumber=5273871&count=156&index=116

@inproceedings{nldb05, author = {Cimiano, Philipp and Völker, Johanna}, title = {Text2Onto - A Framework for Ontology Learning and Data-driven Change Discovery}, editor = {Montoyo, Andres and Munoz, Rafael and Metais, Elisabeth}, booktitle = {Proceedings of the 10th International Conference on Applications of Natural Language to Information Systems (NLDB)}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, address = {Alicante, Spain}, year = {2005}, volume = {3513}, pages = {227-238}, url = {http://www.aifb.uni-karlsruhe.de/WBS/jvo/publications/Text2Onto_nldb_2005.pdf}, keywords = {kaon, learning, nlp, ol, ontology, text2onto} }

%0 = inproceedings %A = Cimiano, Philipp and Völker, Johanna %B = Proceedings of the 10th International Conference on Applications of Natural Language to Information Systems (NLDB) %C = Alicante, Spain %D = 2005 %I = Springer %T = Text2Onto - A Framework for Ontology Learning and Data-driven Change Discovery %U = http://www.aifb.uni-karlsruhe.de/WBS/jvo/publications/Text2Onto_nldb_2005.pdf