CODEWITHSUNDEEP
pythonnltk
Prabhjot Singh Rai
Prabhjot Singh Rai

Reputation: 2545

Where can I find all the tag definitions of POS tagging for ClassifierBasedPOSTagger in NLTK?

I used the following code to train a ClassifierBasedPOSTagger for POS tagging:

from nltk.classify import MaxentClassifier
from nltk.tag.sequential import ClassifierBasedPOSTagger

me_tagger = ClassifierBasedPOSTagger(train=train_sents, classifier_builder=lambda train_feats: MaxentClassifier.train(train_feats, max_iter=15))
print(me_tagger.tag('My new watch is awesome...'.split()))

Which prints out the following tags:

[('My', 'PP$'), ('new', 'JJ'), ('watch', 'NN'), ('is', 'BEZ'), ('awesome...', 'AT')]

Where can I find the token tag definitions for this classifier? I am familiar with these tokens though, but I am unable to construe BEZ and AT.

Upvotes: 0

Views: 199

Answers (2)

alexis
alexis

Reputation: 50220

You should understand that the tagset has nothing to do with the classifier class you chose; the tagset comes from your training data. So your question should have been "where do I find the tag definitions for (this POS-tagged corpus)". You don't say where your train_sents came from, but indeed (as @RAVI already pointed out) these tags seem to come from the Brown corpus; you can read its tagset documentation online, or fetch it from within the nltk like this:

>>> nltk.help.brown_tagset("BEZ")
BEZ: verb 'to be', present tense, 3rd person singular
    is
>>> nltk.help.brown_tagset()   # All tags
...

Upvotes: 1

RAVI
RAVI

Reputation: 3153

You can check - The Brown Corpus Tag-set.

╔═════╦═════════════════════╦════════════════════╗
║ Tag ║ Description         ║ Examples           ║
╠═════╬═════════════════════╬════════════════════╣
║ AT  ║ article             ║ the an no a every  ║
║     ║                     ║ th' ever' ye       ║
╠═════╬═════════════════════╬════════════════════╣
║ BEZ ║ verb "to be",       ║ is                 ║
║     ║ present tense,      ║                    ║
║     ║ 3rd person singular ║                    ║
╠═════╬═════════════════════╬════════════════════╣
║ ... ║ ...                 ║ ...                ║
╚═════╩═════════════════════╩════════════════════╝

Upvotes: 2

Related Questions