Založeno v roce 2005 s podporou MŠMT ČR (projekt 1M0572)

Publikace

Oscillating feature subset search algorithm for text categorization

Typ:
Článek v odborném periodiku
Autoři publikace:
Název periodika:
Lecture Notes in Computer Science
Rok:
2006
Číslo:
4225
Strany:
578-587
ISSN:
0302-9743
Anotace:
The usability of the Oscillating Search algorithm for feature/word selection (FS) in text categorization is explored. The multiclass Bhattacharyya distance for multinomial model as the global feature subset selection criterion for reducing the dimensionality of the bag of words vector document representation is used.This criterion takes into consideration inter-feature relationships.The experiments illustrate that using a non-trivial FS algorithm brings substantial improvement in classification accuracy.
 
Copyright 2005 DAR XHTML CSS