问题
In NLTK, how do I traverse a parsed sentence to return a list of noun phrase strings?
I have two goals:
(1) Create the list of Noun Phrases instead of printing them using the 'traverse()' method. I presently use StringIO to record the output of the existing traverse() method. That is not an acceptable solution.
(2) De-parse the Noun Phrase string so: '(NP Michael/NNP Jackson/NNP)' becomes 'Michael Jackson'. Is there a method in NLTK to de-parse?
The NLTK documentation recommends using traverse() to view the Noun Phrase, but how do I capture the 't' in this recursive method so I generate a list of string Noun Phrases?
from nltk.tag import pos_tag
def traverse(t):
try:
t.label()
except AttributeError:
return
else:
if t.label() == 'NP': print(t) # or do something else
else:
for child in t:
traverse(child)
def nounPhrase(tagged_sent):
# Tag sentence for part of speech
tagged_sent = pos_tag(sentence.split()) # List of tuples with [(Word, PartOfSpeech)]
# Define several tag patterns
grammar = r"""
NP: {<DT|PP\$>?<JJ>*<NN>} # chunk determiner/possessive, adjectives and noun
{<NNP>+} # chunk sequences of proper nouns
{<NN>+} # chunk consecutive nouns
"""
cp = nltk.RegexpParser(grammar) # Define Parser
SentenceTree = cp.parse(tagged_sent)
NounPhrases = traverse(SentenceTree) # collect Noun Phrase
return(NounPhrases)
sentence = "Michael Jackson likes to eat at McDonalds"
tagged_sent = pos_tag(sentence.split())
NP = nounPhrase(tagged_sent)
print(NP)
This presently prints:
(NP Michael/NNP Jackson/NNP)
(NP McDonalds/NNP)
and stores 'None' to NP
回答1:
def extract_np(psent):
for subtree in psent.subtrees():
if subtree.label() == 'NP':
yield ' '.join(word for word, tag in subtree.leaves())
cp = nltk.RegexpParser(grammar)
parsed_sent = cp.parse(tagged_sent)
for npstr in extract_np(parsed_sent):
print (npstr)
来源:https://stackoverflow.com/questions/33815401/nltk-how-do-i-traverse-a-noun-phrase-to-return-list-of-strings