KIT | KIT-Bibliothek | Impressum | Datenschutz

Taxonomy learning: factoring the structure of a taxonomy into a semantic classification decision

Pekar, Viktor; Staab, Steffen

Abstract:

The paper examines different possibilities to take advantage of the taxonomic organization of a thesaurus to improve the accuracy of classifying new words into its classes. The results of the study demonstrate that taxonomic similarity between nearest neighbors, in addition to their distributional similarity to the new word, may be useful evidence on which classification decision can be based.


Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2002
Sprache Englisch
Identifikator KITopen-ID: 34102002
Erschienen in Proceedings of the 19th Conference on Computational Linguistics, COLING 2002, Taipeh, Taiwan 2002
Seiten 786-792.
Externe Relationen Abstract/Volltext
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page