GitHub - benob/french-tagger: Part-of-speech tagger based on CRFSuite, trained for French

benob / french-tagger Public

Notifications You must be signed in to change notification settings
Fork 0
Star 10

Part-of-speech tagger based on CRFSuite, trained for French

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
README		README
add-contextual-features.py		add-contextual-features.py
add-lefff-features.py		add-lefff-features.py
add-morpho-features.py		add-morpho-features.py
crfutils.py		crfutils.py
ftb6.model		ftb6.model
lefff-word-tag.txt		lefff-word-tag.txt
run-tagger.sh		run-tagger.sh
segment-and-tokenize.py		segment-and-tokenize.py
train-tagger.sh		train-tagger.sh

Repository files navigation

Part-of-speech tagger for French.
--------------------------------
Benoit Favre <[email protected]> 2012

Requires CRFSuite 0.12 (http://www.chokkan.org/software/crfsuite/) and python2 or pypy.
crfutils.py and add-contextual-features.py (pos.py) are copied from the CRFSuite source code.

echo Ça le fait. | ./run-tagger.sh 
Ça PRO
le CLO
fait V
. PONCT
 
Trained on the French Treebank 6 (http://www.llf.cnrs.fr/Gens/Abeille/French-Treebank-fr.php) in CoNLL09 format
Word-tag association features are from the Lefff dictionnary (http://alpage.inria.fr/~sagot/lefff-en.html)

$ crfsuite tag -t -q -m ftb6.model ftb6_3.conll09.crfsuite
Item accuracy: 35484 / 36340 (0.9764)
Instance accuracy: 678 / 1235 (0.5490)
Elapsed time: 2.230000 [sec] (553.8 [instance/sec])