... | ... | @@ -33,3 +33,21 @@ Navodila za uporabo programa LemmatizerTrain: |
|
|
Primer uporabe:
|
|
|
|
|
|
LemmatizerTrain -v -t -o -l:SloveneLexicon.txt TrainingCorpus500k.xml LemmatizerModel.bin
|
|
|
|
|
|
Izpis na zaslon:
|
|
|
|
|
|
Nalagam ucni korpus ...
|
|
|
586244 / 586244
|
|
|
Nalagam leksikon ...
|
|
|
2786365
|
|
|
Gradim model za lematizacijo ...
|
|
|
Optimiram lematizacijsko drevo ...
|
|
|
Zapisujem model ...
|
|
|
Koncano.
|
|
|
|
|
|
### Datoteke za prenos ###
|
|
|
|
|
|
* [LemmatizerTrain.exe in pripadajoče datoteke](http://sourceforge.net/projects/obeliks/files/ObeliksReleases/ObeliksMay2012.zip/download) (program)
|
|
|
* [TrainingCorpus500k.xml](http://sourceforge.net/projects/obeliks/files/Resources/TrainingCorpus500k.xml.zip/download) (vhodna datoteka; učni korpus)
|
|
|
* [SloveneLexicon.txt](http://sourceforge.net/projects/obeliks/files/Resources/SloveneLexicon.txt.zip/download) (vhodna datoteka; dodatni učni podatki)
|
|
|
* [LemmatizerModel.bin](http://sourceforge.net/projects/obeliks/files/Resources/LemmatizerModel.bin.zip/download) (izhodna datoteka; model za lematizacijo) |
|
|
\ No newline at end of file |