CODEWITHSUNDEEP
pythonnltk
user2675742
user2675742

Reputation: 117

How do I make NLTK pos_tag words instead of characters?

I have this code to find nouns and verbs in a sentence.

 # -*- coding: utf-8 -*-
from nltk.corpus import wordnet as wn
from nltk import pos_tag
import nltk
syno =[]


sentence = '''His father suggested he study to become a parson instead, but Darwin was far more inclined to study natural history.DarwinDar·win (där'wĭn),Charles Robert.1809-1882.British naturalist who revolutionized the study of biology with his theory ofevolutionbased on natural selection
Like several scientists before him, Darwin believed all the life on earth evolved (developed gradually) over millions of years from a few common ancestors.'''

sent = pos_tag(word_tokenize(sentence))

This returns

[('H', 'NNP'), ('e', 'VBP'), ('l', 'NN'), ('l', 'NN'), ('o', 'NN'), (' ', ':'), ('m', 'NN'), ('y', 'NN'), (' ', ':'), ('n', 'NN'), ('a', 'DT'), ('m', 'NN'), ('e', 'NN'), (' ', ':'), ('i', 'PRP'), ('s', 'VBZ'), (' ', ':'), ('A', 'DT'), ('b', 'NN'), ('h', 'NN'), ('i', 'PRP'), ('s', 'VBZ'), ('h', 'JJ'), ('e', 'NN'), ('k', 'NN'), (' ', ':'), ('M', 'NNP'), ('i', 'PRP'), ('t', 'VBP'), ('r', 'JJ'), ('a', 'DT')]

I want it to operate on words though, not characters! How do I do this?

Upvotes: 3

Views: 8992

Answers (1)

Fred Foo
Fred Foo

Reputation: 363817

You need to tokenize first:

>>> from nltk import pos_tag, word_tokenize
>>> sentence = "Hello my name is Derek. I live in Salt Lake city."
>>> pos_tag(word_tokenize(sentence))
[('Hello', 'NNP'), ('my', 'PRP$'), ('name', 'NN'), ('is', 'VBZ'), ('Derek.', 'NNP'), ('I', 'PRP'), ('live', 'VBP'), ('in', 'IN'), ('Salt', 'NNP'), ('Lake', 'NNP'), ('city', 'NN'), ('.', '.')]

Upvotes: 9

Related Questions