print tagged_sentence
grammar = """
NP: {<DT>?<JJ>?<NN.*>}
ADJP: {<JJ>}
ADVP: {<RB.*>}
PP: {<IN>}
VP: {<MD>?<VB.*>+}
"""
rc = RegexpParser(grammar)
c = rc.parse(tagged_sentence)
print c
print rc.evaluate(test_data)
from nltk.chunk.util import tree2conlltags, conlltags2tree
train_sent = train_data[7]
print train_sent
wtc = tree2conlltags(train_sent)
wtc
tree = conlltags2tree(wtc)
print tree
print tagged_sentence
grammar = """
NP: {<DT>?<JJ>?<NN.*>}
ADJP: {<JJ>}
ADVP: {<RB.*>}
PP: {<IN>}
VP: {<MD>?<VB.*>+}
"""
rc = RegexpParser(grammar)
c = rc.parse(tagged_sentence)
print c
print rc.evaluate(test_data)
from nltk.chunk.util import tree2conlltags, conlltags2tree
train_sent = train_data[7]
print train_sent
wtc = tree2conlltags(train_sent)
wtc
tree = conlltags2tree(wtc)
print tree
grammar = """
NP: {<DT>?<JJ>?<NN.*>}
ADJP: {<JJ>}
ADVP: {<RB.*>}
PP: {<IN>}
VP: {<MD>?<VB.*>+}
"""
rc = RegexpParser(grammar)
c = rc.parse(tagged_sentence)
print
c
print
rc.evaluate(test_data)
from nltk.chunk.util import tree2conlltags, conlltags2tree
train_sent = train_data[7]
print
train_sent
wtc = tree2conlltags(train_sent)
wtc
tree = conlltags2tree(wtc)
print
tree
print(tagged_sentence)
grammar = """
NP: {<DT>?<JJ>?<NN.*>}
ADJP: {<JJ>}
ADVP: {<RB.*>}
PP: {<IN>}
VP: {<MD>?<VB.*>+}
"""
rc = RegexpParser(grammar)
c = rc.parse(tagged_sentence)
print(c)
print(rc.evaluate(test_data))
from nltk.chunk.util import tree2conlltags, conlltags2tree
train_sent = train_data[7]
print(train_sent)
wtc = tree2conlltags(train_sent)
wtc
tree = conlltags2tree(wtc)
print(tree)
# Making a chunker and testing it's accuracy
# 1.1: Chunk optional determiner with nouns
# 1.2: Merge adjective with noun chunk
# 2.1: Chunk preposition
# 3.1: Chunk optional modal with verb
chunker = RegexpParser(r'''
NP:
{<DT>?<NN.*>+}
<JJ>{}<NN.*>
PP:
{<IN>}
VP:
{<MD>?<VB.*>}
''')
score = chunker.evaluate(conll2000.chunked_sents())
print(f"Accuracy of regex chunker: {score.accuracy()}")
# Tagger-based chunker
def conll_tag_chunks(chunk_sents):
"""
Extracts a list of tuples (pos, iob) from a list of trees.
"""
tagged_sents = [tree2conlltags(tree) for tree in chunk_sents]
return [[(t, c) for (w, t, c) in sent] for sent in tagged_sents]
def make_backoffs(training, tagger_classes, backoff=None):
"""
