def demo(**kwargs):
import nltk
from nltk_contrib.coref import NLTK_COREF_DATA
from nltk_contrib.coref.muc import muc6_documents, muc7_documents
from nltk_contrib.coref.muc import MUCCorpusReader
nltk.data.path.insert(0, NLTK_COREF_DATA)
muc6 = LazyCorpusLoader('muc6/', MUCCorpusReader, muc6_documents)
for sent in muc6.iob_sents()[:]:
for word in sent:
print word
print
print
for sent in muc6.mentions(depth=None):
for mention in sent:
print mention
if sent: print
print
muc7 = LazyCorpusLoader('muc7/', MUCCorpusReader, muc7_documents)
for sent in muc7.iob_sents()[:]:
for word in sent:
print word
print
print
for sent in muc7.mentions(depth=None):
for mention in sent:
print mention
if sent: print
print
def demo(**kwargs):
import nltk
from nltk_contrib.coref import NLTK_COREF_DATA
from nltk_contrib.coref.muc import muc6_documents, muc7_documents
from nltk_contrib.coref.muc import MUCCorpusReader
nltk.data.path.insert(0, NLTK_COREF_DATA)
muc6 = LazyCorpusLoader('muc6/', MUCCorpusReader, muc6_documents)
for sent in muc6.iob_sents()[:]:
for word in sent:
print word
print
print
for sent in muc6.mentions(depth=None):
for mention in sent:
print mention
if sent: print
print
muc7 = LazyCorpusLoader('muc7/', MUCCorpusReader, muc7_documents)
for sent in muc7.iob_sents()[:]:
for word in sent:
print word
print
print
for sent in muc7.mentions(depth=None):
for mention in sent:
print mention
if sent: print
print
treebank_test_sequence = treebank_test.tagged_sents()
treebank_estimator = LidstoneProbDistFactory
model = train_model(HiddenMarkovModelTagger,
treebank_train_sequence,
treebank_test_sequence,
options.model_file,
options.num_train_sents,
options.num_test_sents,
estimator=treebank_estimator,
verbose=options.verbose)
elif options.train_chunker:
conll2k_train = LazyCorpusLoader(
'conll2000', ConllChunkCorpusReader,
['train.txt'], ('NP','VP','PP'))
conll2k_train_sequence = conll2k_train.iob_sents()
conll2k_test = LazyCorpusLoader(
'conll2000', ConllChunkCorpusReader,
['test.txt'], ('NP','VP','PP'))
conll2k_test_sequence = conll2k_test.iob_sents()
conll2k_estimator = LidstoneProbDistFactory
conll2k_transform = ClosedCategoryChunkTransform(TREEBANK_CLOSED_CATS)
model = train_model(HiddenMarkovModelChunkTagger,
conll2k_train_sequence,
conll2k_test_sequence,
options.model_file,
options.num_train_sents,
options.num_test_sents,
estimator=conll2k_estimator,
transform=conll2k_transform,
verbose=options.verbose)
