In [1]:

    

import nltk
sentence = "Hello my name is joe."
tokens = nltk.word_tokenize(sentence)
tokens


    

    
Out[1]:





['Hello', 'my', 'name', 'is', 'joe', '.']

In [2]:

    

tagged = nltk.pos_tag(tokens)


    

In [3]:

    

tagged


    

    
Out[3]:





[('Hello', 'NNP'),
 ('my', 'PRP$'),
 ('name', 'NN'),
 ('is', 'VBZ'),
 ('joe', 'NN'),
 ('.', '.')]

In [4]:

    

entities = nltk.chunk.ne_chunk(tagged)


    

In [5]:

    

type(entities)


    

    
Out[5]:





nltk.tree.Tree

In [6]:

    

%pylab inline


    

    




Populating the interactive namespace from numpy and matplotlib

In [7]:

    

from nltk.corpus import treebank


    

In [8]:

    

t = treebank.parsed_sents('wsj_0001.mrg')[0]


    

In [9]:

    

t.draw()


    

In [ ]: