%0 Book Section %1 chung2006webbased %A Chung, Seokkyung %A Jun, Jongeun %A McLeod, Dennis %B On the Move to Meaningful Internet Systems 2006: CoopIS, DOA, GADA, and ODBASE %C Berlin / Heidelberg %D 2006 %E Meersman, Robert %E Tari, Zahir %I Springer %K ol_web2.0 widely_related %P 1092-1109 %R 10.1007/11914853_70 %T A Web-Based Novel Term Similarity Framework for Ontology Learning %U http://dx.doi.org/10.1007/11914853_70 %V 4275 %X Given that pairwise similarity computations are essential in ontology learning and data mining, we propose a similarity framework that is based on a conventional Web search engine. There are two main aspects that we can benefit from utilizing a Web search engine. First, we can obtain the freshest content for each term that represents the up-to-date knowledge on the term. This is particularly useful for dynamic ontology management in that ontologies must evolve with time as new concepts or terms appear. Second, in comparison with the approaches that use the certain amount of crawled Web documents as corpus, our method is less sensitive to the problem of data sparseness because we access as much content as possible using a search engine. At the core of our proposed methodology, we present two different measures for similarity computation, a mutual information based and a feature-based metric. Moreover, we show how the proposed metrics can be utilized for modifying existing ontologies. Finally, we compare the extracted similarity relations with semantic similarity using WordNet. Experimental results show that our method can extract topical relations between terms that are not present in conventional concept-based ontologies.

@incollection{chung2006webbased, abstract = {Given that pairwise similarity computations are essential in ontology learning and data mining, we propose a similarity framework that is based on a conventional Web search engine. There are two main aspects that we can benefit from utilizing a Web search engine. First, we can obtain the freshest content for each term that represents the up-to-date knowledge on the term. This is particularly useful for dynamic ontology management in that ontologies must evolve with time as new concepts or terms appear. Second, in comparison with the approaches that use the certain amount of crawled Web documents as corpus, our method is less sensitive to the problem of data sparseness because we access as much content as possible using a search engine. At the core of our proposed methodology, we present two different measures for similarity computation, a mutual information based and a feature-based metric. Moreover, we show how the proposed metrics can be utilized for modifying existing ontologies. Finally, we compare the extracted similarity relations with semantic similarity using WordNet. Experimental results show that our method can extract topical relations between terms that are not present in conventional concept-based ontologies.}, added-at = {2011-02-17T17:41:55.000+0100}, address = {Berlin / Heidelberg}, affiliation = {Yahoo! Inc., 2821 Mission College Blvd, Santa Clara, CA 95054 USA USA}, author = {Chung, Seokkyung and Jun, Jongeun and McLeod, Dennis}, biburl = {https://www.bibsonomy.org/bibtex/2abc370e27adf82c389b3a96dbcffb866/dbenz}, booktitle = {On the Move to Meaningful Internet Systems 2006: CoopIS, DOA, GADA, and ODBASE}, description = {SpringerLink - Abstract}, doi = {10.1007/11914853_70}, editor = {Meersman, Robert and Tari, Zahir}, file = {chung2006webbased.pdf:chung2006webbased.pdf:PDF}, groups = {public}, interhash = {dc3c95f48bc109fce13b027443c8c96d}, intrahash = {abc370e27adf82c389b3a96dbcffb866}, keywords = {ol_web2.0 widely_related}, pages = {1092-1109}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2013-07-31T15:39:42.000+0200}, title = {A Web-Based Novel Term Similarity Framework for Ontology Learning}, url = {http://dx.doi.org/10.1007/11914853_70}, username = {dbenz}, volume = 4275, workshoppub = {1}, year = 2006 }