StanfordParser Test Code

output.md

[(u'While', u'O'), (u'in', u'O'), (u'France', u'LOCATION'), (u',', u'O'), (u'Christine', u'PERSON'), (u'Lagarde', u'PERSON'), (u'discussed', u'O'), (u'short-term', u'O'), (u'stimulus', u'O'), (u'efforts', u'O'), (u'in', u'O'), (u'a', u'O'), (u'recent', u'O'), (u'interview', u'O'), (u'with', u'O'), (u'the', u'O'), (u'Wall', u'ORGANIZATION'), (u'Street', u'ORGANIZATION'), (u'Journal', u'ORGANIZATION'), (u'.', u'O')]

stanford_ner_test.py

from nltk.tag import StanfordNERTagger
from nltk.tokenize import word_tokenize

# Change the path according to your system
stanford_classifier = 'D:\StanfordParser\stanford-ner-2015-12-09\classifiers\english.all.3class.distsim.crf.ser.gz'
stanford_ner_path = 'D:\StanfordParser\stanford-ner-2015-12-09\stanford-ner.jar'

# Creating Tagger Object
st = StanfordNERTagger(stanford_classifier, stanford_ner_path, encoding='utf-8')

text = 'While in France, Christine Lagarde discussed short-term stimulus efforts in a recent interview with the Wall Street Journal.'

tokenized_text = word_tokenize(text)
classified_text = st.tag(tokenized_text)

print classified_text