train_data = brown_tagged_sents[:int(len(brown_tagged_sents) * 0.9)]
test_data = brown_tagged_sents[int(len(brown_tagged_sents) * 0.9):]
unigram_tagger = UnigramTagger(train_data, backoff=default_tagger)
print(unigram_tagger.evaluate(test_data))
# 0.835841722316356
bigram_tagger = BigramTagger(train_data, backoff=unigram_tagger)
print(bigram_tagger.evaluate(test_data))
# 0.8454101465164956
trigram_tagger = TrigramTagger(train_data, backoff=bigram_tagger)
print(trigram_tagger.evaluate(test_data))
# 0.8427190272102063
regexp_tagger = RegexpTagger(
[( r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers
( r'(The|the|A|a|An|an)$', 'AT'), # articles
( r'.*able$', 'JJ'), # adjectives
( r'.*ness$', 'NN'), # nouns formed from adj
( r'.*ly$', 'RB'), # adverbs
( r'.*s$', 'NNS'), # plural nouns
( r'.*ing$', 'VBG'), # gerunds
(r'.*ed$', 'VBD'), # past tense verbs
(r'.*', 'NN') # nouns (default)
])
print(regexp_tagger.evaluate(test_data))
# 0.31306687929831556
def train(self, templates=None, verbose=True):
"""Train a new Brill tagger."""
if templates is None:
templates = brill.nltkdemo18()
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# very simple regular expression tagger
regex_tagger = RegexpTagger([(r'^-?[0-9]+(.[0-9]+)?$', 'PUNCT'),
(r'.*', 'N')])
if verbose == True:
print "Regular expression tagger accuracy:\n{}\n".format(
regex_tagger.evaluate(test_data))
# unigram tagger
unigram_tagger = UnigramTagger(train=training_data,
backoff=regex_tagger)
if verbose == True:
print "Unigram tagger accuracy:\n{}\n".format(
unigram_tagger.evaluate(test_data))
# bigram tagger
bigram_tagger = BigramTagger(train=training_data,
backoff=unigram_tagger)
if verbose == True:
print "Bigram tagger accuracy:\n{}\n".format(
bigram_tagger.evaluate(test_data))
# trigram tagger
trigram_tagger = TrigramTagger(train=training_data,
backoff=bigram_tagger)
if verbose == True:
print "Trigram tagger accuracy:\n{}\n".format(
trigram_tagger.evaluate(test_data))
# first iteration
trainer = BrillTaggerTrainer(initial_tagger=trigram_tagger,
templates=templates)
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Initial Brill tagger accuracy:\n{}\n".format(
brill_tagger.evaluate(test_data))
# folding
for i in range(0, self.num_groups):
# random splitting
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# note that .train method returns a BrillTagger() object
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Brill tagger accuracy, fold {}:\n{}\n".format(
i + 1, brill_tagger.evaluate(test_data))
# Regex tagger
>>>from nltk.tag.sequential import RegexpTagger
>>>regexp_tagger = RegexpTagger(
[( r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers
( r'(The|the|A|a|An|an)$', 'AT'), # articles
( r'.*able$', 'JJ'), # adjectives
( r'.*ness$', 'NN'), # nouns formed from adj
( r'.*ly$', 'RB'), # adverbs
( r'.*s$', 'NNS'), # plural nouns
( r'.*ing$', 'VBG'), # gerunds
(r'.*ed$', 'VBD'), # past tense verbs
(r'.*', 'NN') # nouns (default)
])
>>>print regexp_tagger.evaluate(test_data)
# NER tagger
>>>import nltk
>>>from nltk import ne_chunk
>>>from nltk import word_tokenize
>>>sent = "Mark is studying at Stanford University in California"
>>>print(ne_chunk(nltk.pos_tag(word_tokenize(sent)), binary=False))
# NER stanford tagger
>>>from nltk.tag.stanford import NERTagger
>>>st = NERTagger('<PATH>/stanford-ner/classifiers/all.3class.distsim.crf.ser.gz',... '<PATH>/stanford-ner/stanford-ner.jar')
# <PATH> will be the relative path where you downloaded the tagger
def train(self, templates=None, verbose=True):
"""Train a new Brill tagger."""
if templates is None:
templates = brill.nltkdemo18()
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# very simple regular expression tagger
regex_tagger = RegexpTagger([
(r'^-?[0-9]+(.[0-9]+)?$', 'PUNCT'),
(r'.*', 'N')
])
if verbose == True:
print "Regular expression tagger accuracy:\n{}\n".format(
regex_tagger.evaluate(test_data))
# unigram tagger
unigram_tagger = UnigramTagger(train=training_data,
backoff=regex_tagger)
if verbose == True:
print "Unigram tagger accuracy:\n{}\n".format(
unigram_tagger.evaluate(test_data))
# bigram tagger
bigram_tagger = BigramTagger(train=training_data,
backoff=unigram_tagger)
if verbose == True:
print "Bigram tagger accuracy:\n{}\n".format(
bigram_tagger.evaluate(test_data))
# trigram tagger
trigram_tagger = TrigramTagger(train=training_data,
backoff=bigram_tagger)
if verbose == True:
print "Trigram tagger accuracy:\n{}\n".format(
trigram_tagger.evaluate(test_data))
# first iteration
trainer = BrillTaggerTrainer(initial_tagger=trigram_tagger,
templates=templates)
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Initial Brill tagger accuracy:\n{}\n".format(
brill_tagger.evaluate(test_data))
# folding
for i in range(0, self.num_groups):
# random splitting
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# note that .train method returns a BrillTagger() object
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Brill tagger accuracy, fold {}:\n{}\n".format(
i+1, brill_tagger.evaluate(test_data))
