In [26]:

    

from nltk.corpus.reader import TaggedCorpusReader
from nltk.tag import BigramTagger
from nltk.tag import TrigramTagger
from nltk.tag import UnigramTagger
from nltk.tokenize import wordpunct_tokenize


    

In [28]:

    

#trainer
reader = TaggedCorpusReader('.', 'latin_training_set.pos')
train_sents = reader.tagged_sents()


    

In [31]:

    

tagger1 = UnigramTagger(train_sents)


    

In [32]:

    

tagger2 = BigramTagger(train_sents, backoff=tagger1)


    

In [33]:

    

tagger3 = TrigramTagger(train_sents, backoff=tagger2)


    

In [35]:

    

tagger3.evaluate(train_sents)


    

    
Out[35]:





0.9796586568315676