Stemmers

[Marcelo Pita]

Hello,

I would like to know how to use a Brazilian Portuguese stemmer in the StringToWordVector filter. I tried to put the SnowballStemmer (visible through CLASSPATH), but results seems to be the same as those with no stemmer. Another doubt is how the SnowballStemmer considers the Brazilian Portuguese vacabulary instead of any other.

Thank you very much in advance!

Cheers,
Marcelo Pita


_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@...
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

[Peter Reutemann-3]

> I would like to know how to use a Brazilian Portuguese stemmer in the
> StringToWordVector filter. I tried to put the SnowballStemmer (visible
> through CLASSPATH), but results seems to be the same as those with no
> stemmer. Another doubt is how the SnowballStemmer considers the Brazilian
> Portuguese vacabulary instead of any other.

While browsing the subversion repository of the Snowball stemmers, I
came across the mentioning of the PTStemmer library:
  http://svn.tartarus.org/snowball/trunk/website/otherlangs/portuguese_java.txt?view=markup&pathrev=509
  http://code.google.com/p/ptstemmer/

I've hacked together a little stemmer plugin based on the PTStemmer
library. See section "PTStemmer" in the wiki article "Stemmers":
  http://weka.wikispaces.com/Stemmers

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
http://www.cs.waikato.ac.nz/~fracpete/           Ph. [phone]

_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@...
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html