GitHub

This is the Natural Language Processing program dealing with English Lexical Substitution Task of SemEval-2007 Task 10.

The algorithm I use named LESK which is an unsupervised learning.

Please intall the NLTK toolbox before using it.

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
BL.out		BL.out
README.md		README.md
cosine.py		cosine.py
cosine.pyc		cosine.pyc
gold.trial		gold.trial
lesk.py		lesk.py
lesk.pyc		lesk.pyc
lexsub_trial.parsed.xml		lexsub_trial.parsed.xml
lexsub_trial.sents.txt		lexsub_trial.sents.txt
lexsub_trial.targets.tsv		lexsub_trial.targets.tsv
lexsub_trial.xml		lexsub_trial.xml
lexsub_trial_idmap.tsv		lexsub_trial_idmap.tsv
main.py		main.py
predominantsense.py		predominantsense.py
result.txt		result.txt
score.pl		score.pl
subs_system.py		subs_system.py

fieryfish/wordSubstitutionTask