Víceslovné výrazy a klasifikace českých textů

Warning

This publication doesn't include Faculty of Sports Studies. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Title in English	Multiword expressions and Czech document classification
Authors	MRÁKOVÁ Eva POPELÍNSKÝ Lubomír BLAŤÁK Jan
Year of publication	2004
Type	Article in Proceedings
Conference	Znalosti 2004, sborník posterů
MU Faculty or unit	Faculty of Informatics
Citation
Field	Informatics
Keywords	text classification; machine learning; multword expressions
Description	The use of chunks - noun, verb and prepositional phrases - as new features in Czech text classification is discussed, and the most interesting as well as the most useful chunks found are introduced. We also mention the role of lemmatization in Czech text classification.
Related projects:	Human-computer interaction, dialog systems and assistive technologies