Fran Ramovš Institute of the Slovenian Language at ZRC SAZU
Corpus Laboratory

Lemmas and word classes/POS tags from wordforms

        Enter the list, word per line, into the dialog window and click the "Submit" bar. The words may be followed in the same line by frequencies, separated by an upper dot (i.e. polovinke·23) or the hash sign (i.e. umetnosti#172). To get reasonable response times it is recommended that the list is kept moderate - up to a few thousand words.
        Copy the letters č, ž and š from this line if they are required but are not accessible through the keyboard.
        Example: try jaz, morje, peči - enter each word into a new line.

Word classes      POS tags


Please direct inquiries and comments to P. Jakopin. The tagset by Aleksandra Bizjak - see the paper Part-of-speech tagging of Slovenian text (Slavistična revija, Vol. 45/3-4, 1997, str. 513-532), or. its extended English summary.

Page posted September 22, 2008. Date of last change: September 26.