Recent work has shown improvements in text clustering and classification tasks by integrating conceptual features extracted from ontologies. In this paper we present text mining experiments in the medical domain in which the ontological structures used are acquired automatically in an unsupervised learning process from the text corpus in question. We compare results obtained using the automatically learned ontologies with those obtained using manually engineered ones. Our results show that both types of ontologies improve results on text clustering and classification tasks, whereby the automatically acquired ontologies yield a improvement competitive with the manually engineered ones.
-

@incollection{bloehdorn2006learning, author = {Bloehdorn, Stephan and Cimiano, Philipp and Hotho, Andreas}, title = {Learning Ontologies to Improve Text Clustering and Classification}, booktitle = {From Data and Information Analysis to Knowledge Engineering}, publisher = {Springer Berlin Heidelberg}, year = {2006}, pages = {334--341}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2006/2006-03-gfkl05-bloehdorn-etal-learning-ontologies.pdf}, doi = {http://dx.doi.org/10.1007/3-540-31314-1_40}, isbn = {978-3-540-31313-7}, keywords = {classification, text, clustering, 2006, ol, myown}, abstract = {Recent work has shown improvements in text clustering and classification tasks by integrating conceptual features extracted from ontologies. In this paper we present text mining experiments in the medical domain in which the ontological structures used are acquired automatically in an unsupervised learning process from the text corpus in question. We compare results obtained using the automatically learned ontologies with those obtained using manually engineered ones. Our results show that both types of ontologies improve results on text clustering and classification tasks, whereby the automatically acquired ontologies yield a improvement competitive with the manually engineered ones.
-} }

%0 = incollection %A = Bloehdorn, Stephan and Cimiano, Philipp and Hotho, Andreas %B = From Data and Information Analysis to Knowledge Engineering %D = 2006 %I = Springer Berlin Heidelberg %T = Learning Ontologies to Improve Text Clustering and Classification %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2006/2006-03-gfkl05-bloehdorn-etal-learning-ontologies.pdf

@inproceedings{cim04a, author = {Cimiano, Philipp and Hotho, Andreas and Staab, Steffen}, title = {Clustering Ontologies from Text}, booktitle = {Proceedings of the Conference on Languages Resources and Evaluation (LREC)}, publisher = {ELRA - European Language Ressources Association}, address = {Lisbon, Portugal}, year = {2004}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/lrec04.pdf}, keywords = {2004, text, clustering, ol, myown, ontology} }

%0 = inproceedings %A = Cimiano, Philipp and Hotho, Andreas and Staab, Steffen %B = Proceedings of the Conference on Languages Resources and Evaluation (LREC) %C = Lisbon, Portugal %D = 2004 %I = ELRA - European Language Ressources Association %T = Clustering Ontologies from Text %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2004/lrec04.pdf

The application of clustering methods for automatic taxonomy construction from text requires knowledge about the tradeoff between, (i), their effectiveness (quality of result), (ii), efficiency (run-time behaviour), and, (iii), traceability of the taxonomy construction by the ontology engineer. In this line, we present an original conceptual clustering method based on Formal Concept Analysis for automatic taxonomy construction and compare it with hierarchical agglomerative clustering and hierarchical divisive clustering.

@inproceedings{cimiano2004comparing, author = {Cimiano, Philipp and Hotho, Andreas and Staab, Steffen}, title = {Comparing Conceptual, Divise and Agglomerative Clustering for Learning Taxonomies from Text}, editor = {de Mántaras, R. López and Saitta, L.}, booktitle = {ECAI 2004 Proceedings of the 16th European Conference on Artificial Intelligence, 22 - 27 August, Valencia, Spain}, publisher = {IOS Press}, year = {2004}, pages = {435-439}, keywords = {ol_web2.0, methods_from_text, clustering, ontology_learning, taxonomy_learning}, abstract = {The application of clustering methods for automatic taxonomy construction from text requires knowledge about the tradeoff between, (i), their effectiveness (quality of result), (ii), efficiency (run-time behaviour), and, (iii), traceability of the taxonomy construction by the ontology engineer. In this line, we present an original conceptual clustering method based on Formal Concept Analysis for automatic taxonomy construction and compare it with hierarchical agglomerative clustering and hierarchical divisive clustering.} }

%0 = inproceedings %A = Cimiano, Philipp and Hotho, Andreas and Staab, Steffen %B = ECAI 2004 Proceedings of the 16th European Conference on Artificial Intelligence, 22 - 27 August, Valencia, Spain %D = 2004 %I = IOS Press %T = Comparing Conceptual, Divise and Agglomerative Clustering for Learning Taxonomies from Text

@inproceedings{cim04c, author = {Cimiano, Philipp and Hotho, Andreas and Staab, Steffen}, title = {Comparing Conceptual, Divise and Agglomerative Clustering for Learning Taxonomies from Text}, editor = {de Mántaras, Ramon López and Saitta, Lorenza}, booktitle = {Proceedings of the European Conference on Artificial Intelligence (ECAI'04)}, publisher = {IOS Press}, address = {Valencia, Spain}, year = {2004}, pages = {435-439}, url = {http://www.kde.cs.uni-kassel.de/hotho/pub/2004/ecai04.pdf}, isbn = {1-58603-452-9}, keywords = {2004, clustering, taxonomies, learning, myown} }

%0 = inproceedings %A = Cimiano, Philipp and Hotho, Andreas and Staab, Steffen %B = Proceedings of the European Conference on Artificial Intelligence (ECAI'04) %C = Valencia, Spain %D = 2004 %I = IOS Press %T = Comparing Conceptual, Divise and Agglomerative Clustering for Learning Taxonomies from Text %U = http://www.kde.cs.uni-kassel.de/hotho/pub/2004/ecai04.pdf