class Tagger:
"""Tag words' part of speech in sentences."""
def __init__(self):
self.tagger = SennaTagger('/app/util/senna')
def tag(self, tokens_in_sentence):
"""Tag tokens in sentences with their part of speech.
:param tokens_in_sentence: list of tokens, grouped by sentence.
:return: iterator of lists with words.
"""
return ((Word(t, self._parse_POS(POS)) for t, POS in s)
for s in self.tagger.tag_sents(tokens_in_sentence))
def _parse_POS(self, tag):
if tag.startswith('J'):
return PartOfSpeach.ADJECTIVE
elif tag.startswith('V'):
return PartOfSpeach.VERB
elif tag.startswith('N'):
return PartOfSpeach.NOUN
elif tag.startswith('R'):
return PartOfSpeach.ADVERB
return PartOfSpeach.OTHER
# -*- coding: utf-8 -*-
"""
Created on Sun May 14 12:37:50 2017
@author: Shanika Ediriweera
"""
from nltk import word_tokenize
from nltk.tag import SennaTagger
senna = SennaTagger('../../tools/senna')
sents = ["All the banks are closed", "Today is Sunday"]
tokenized_sents = [word_tokenize(sent) for sent in sents]
print(senna.tag_sents(tokenized_sents))
