|
|
| Zeile 16: |
Zeile 16: |
| | }} | | }} |
| | {{Publikation Details | | {{Publikation Details |
| − | |Abstract=Common clustering techniques have the disadvantage that they do not provide intensional descriptions of the clusters obtained. Conceptual Clustering techniques, on the other hand, provide such descriptions, but are known to be rather slow. In this paper, we discuss a way of combining both techniques. We first cluster the documents by avariant of k {Means, using a thesaurus as background
| + | |Forschungsgruppe=Wissensmanagement |
| − | knowledge. This clustering reduces the large number of documents to a relatively small number of clusters, which can then be clustered conceptually in the second step.
| |
| − | |VG Wort-Seiten=
| |
| − | |Download=2002_20_Hotho_Conceptual_Clus_1.pdf
| |
| − | |Projekt=
| |
| − | |Forschungsgruppe=Effiziente Algorithmen, | |
| − | }}
| |
| − | {{Forschungsgebiet Auswahl
| |
| − | |Forschungsgebiet=Formale Begriffsanalyse
| |
| − | }}
| |
| − | {{Forschungsgebiet Auswahl
| |
| − | |Forschungsgebiet=Text Mining
| |
| − | }}
| |
| − | {{Forschungsgebiet Auswahl
| |
| − | |Forschungsgebiet=Wissensmanagement
| |
| | }} | | }} |
Aktuelle Version vom 24. September 2009, 15:44 Uhr
Conceptual Clustering of Text Clusters
Published: 2002
Herausgeber: G. Kókai, J. Zeidler (Eds.)
Buchtitel: Proc. Fachgruppentreffen Maschinelles Lernen (FGML 2002), 7.-9.10.2002, Hannover
Seiten: 37-45
Referierte Veröffentlichung
BibTeX
Forschungsgruppe
Wissensmanagement
Forschungsgebiet
