Create a gist now

Instantly share code, notes, and snippets.

Basic example of using NLTK for name entity extraction.
import nltk
with open('sample.txt', 'r') as f:
sample = f.read()
sentences = nltk.sent_tokenize(sample)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
chunked_sentences = nltk.batch_ne_chunk(tagged_sentences, binary=True)
def extract_entity_names(t):
entity_names = []
if hasattr(t, 'node') and t.node:
if t.node == 'NE':
entity_names.append(' '.join([child[0] for child in t]))
else:
for child in t:
entity_names.extend(extract_entity_names(child))
return entity_names
entity_names = []
for tree in chunked_sentences:
# Print results per sentence
# print extract_entity_names(tree)
entity_names.extend(extract_entity_names(tree))
# Print all entity names
#print entity_names
# Print unique entity names
print set(entity_names)
@rsingh2083

Im sorry but your code isnt working ---- nltk.batch_ne_chunk : 'module' object has no attribute 'batch_ne_chunk'
Please suggest what to do

@hugokoopmans

hi Rsingh, the NLTK 3.0 docs say 😄 chunk.batch_ne_chunk() → chunk.ne_chunk_sents()
i replaced that and script works again ...

hugo

@hugokoopmans

also seems there is more changes in NLTK 3.0

also change this 'node' to 'label()' :

if hasattr(t, 'label') and t.label:
    if t.label() == 'NE':
@ririw

For future readers, here's a version that works for me, using NLTK version 3.0.3

import nltk 
with open('sample.txt', 'r') as f:
    sample = f.read()


sentences = nltk.sent_tokenize(sample)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
chunked_sentences = nltk.ne_chunk_sents(tagged_sentences, binary=True)

def extract_entity_names(t):
    entity_names = []

    if hasattr(t, 'label') and t.label:
        if t.label() == 'NE':
            entity_names.append(' '.join([child[0] for child in t]))
        else:
            for child in t:
                entity_names.extend(extract_entity_names(child))

    return entity_names

entity_names = []
for tree in chunked_sentences:
    # Print results per sentence
    # print extract_entity_names(tree)

    entity_names.extend(extract_entity_names(tree))

# Print all entity names
#print entity_names

# Print unique entity names
print set(entity_names)
@matthewcornell

Thanks for this.

@Rahulvks

Am facing error when in run the code !!

UnicodeDecodeError: 'ascii' codec can't decode byte 0x8e in position 518: ordinal not in range(128)

@hongtao510

Try
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

@loretoparisi
 Resource u'chunkers/maxent_ne_chunker/english_ace_binary.pickle'
  not found.  Please use the NLTK Downloader to obtain the
  resource:  >>> nltk.download()
  Searched in:
    - '/Users/admin/nltk_data'
    - '/usr/share/nltk_data'
    - '/usr/local/share/nltk_data'
    - '/usr/lib/nltk_data'
    - '/usr/local/lib/nltk_data'
    - u''
@dibosh

@loretoparisi download the necessary dependencies-

nltk.download('maxent_ne_chunker')
nltk.download('words')

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment