Context-based Hierarchical Clustering for the Ontology Learning

@inproceedings{citeulike:1216173, abstract = {Ontologies provide a common layer which plays a major role in supporting information exchange and sharing. In this paper, we focus on the ontological concept extraction process from HTML documents. In order to improve this process, we propose an unsupervised hierarchical clustering algorithm namely "Contextual Ontological Concept Extraction" (COCE) which is an incremental use of the partitioning algorithm Kmeans and is guided by a structural context. Our context exploits the html structure and the location of words to select the semantically closer cooccurrents for each word and to improve the words weighting. Guided by this context definition, we perform an incremental clustering that refines the context of each word clusters to obtain semantically extracted concepts. The COCE algorithm offers the choice between either an automatic execution or a user\^{A}¿s interaction. We experiment our algorithm on HTML documents related to the tourism domain. Our results show how the execution of our context-based algorithm which implements an incremental process and a successive refinement of clusters improves their conceptual quality and the relevance of the extracted ontological concepts.}, author = {Karoui, L. and Aufaure, M. A. and Bennacer, N. }, citeulike-article-id = {1216173}, journal = {Web Intelligence, 2006. WI 2006. IEEE/WIC/ACM International Conference on}, keywords = {clustering, context, ontology, semantic}, pages = {420--427}, posted-at = {2007-04-08 19:28:53}, priority = {0}, title = {Context-based Hierarchical Clustering for the Ontology Learning}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=4061406}, year = {2006} }

TY - CONF ID - citeulike:1216173 L3 - citeulike-article-id:1216173 N2 - Ontologies provide a common layer which plays a major role in supporting information exchange and sharing. In this paper, we focus on the ontological concept extraction process from HTML documents. In order to improve this process, we propose an unsupervised hierarchical clustering algorithm namely "Contextual Ontological Concept Extraction" (COCE) which is an incremental use of the partitioning algorithm Kmeans and is guided by a structural context. Our context exploits the html structure and the location of words to select the semantically closer cooccurrents for each word and to improve the words weighting. Guided by this context definition, we perform an incremental clustering that refines the context of each word clusters to obtain semantically extracted concepts. The COCE algorithm offers the choice between either an automatic execution or a user¿s interaction. We experiment our algorithm on HTML documents related to the tourism domain. Our results show how the execution of our context-based algorithm which implements an incremental process and a successive refinement of clusters improves their conceptual quality and the relevance of the extracted ontological concepts. JF - Web Intelligence, 2006. WI 2006. IEEE/WIC/ACM International Conference on EP - 427 TI - Context-based Hierarchical Clustering for the Ontology Learning SP - 420 KW - clustering KW - context KW - ontology KW - semantic AU - Karoui, L AU - Aufaure, MA AU - Bennacer, N PY - 2006/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4061406 ER -