CODEWITHSUNDEEP
pythontext-parsingnltkchunking
Vincent Theeten
Vincent Theeten

Reputation: 251

NLTK Chunking and walking the results tree

I'm using NLTK RegexpParser to extract noungroups and verbgroups from tagged tokens.

How do I walk the resulting tree to find only the chunks that are NP or V groups?

from nltk.chunk import RegexpParser

grammar = '''
NP: {<DT>?<JJ>*<NN>*}
V: {<V.*>}'''
chunker = RegexpParser(grammar)
token = [] ## Some tokens from my POS tagger
chunked = chunker.parse(tokens)
print chunked

#How do I walk the tree?
#for chunk in chunked:
#    if chunk.??? == 'NP':
#         print chunk

(S (NP Carrier/NN) for/IN tissue-/JJ and/CC cell-culture/JJ for/IN (NP the/DT preparation/NN) of/IN (NP implants/NNS) and/CC (NP implant/NN) (V containing/VBG) (NP the/DT carrier/NN) ./.)

Upvotes: 13

Views: 7476

Answers (4)

Raoof Naushad
Raoof Naushad

Reputation: 876

def preprocess(sent):
sent = nltk.word_tokenize(sent)
sent = nltk.pos_tag(sent)
return sent



pattern = 'NP: {<JJ>*<NNP.*>*}'
cp =   nltk.RegexpParser(pattern)
exp = []
for line in lines:
    line = preprocess(line)
    cs = cp.parse(line)
    for n in cs:
        if isinstance(n, nltk.tree.Tree):
            if n.label() == 'NP':
                if len(n.leaves()) > 1:
                    req = ''
                    for leaf in n.leaves():
                        req += leaf[0]+' '
                    exp.append(req)
print(exp)

Upvotes: 0

Savino Sguera
Savino Sguera

Reputation: 3572

This should work:

for n in chunked:
    if isinstance(n, nltk.tree.Tree):               
        if n.label() == 'NP':
            do_something_with_subtree(n)
        else:
            do_something_with_leaf(n)

Upvotes: 13

TheKevJames
TheKevJames

Reputation: 101

Savino's answer is great, but it's also worth noting that subtrees can be accessed by index as well, e.g.

for n in range(len(chunked)):
    do_something_with_subtree(chunked[n])

Upvotes: 0

Wasim Karani
Wasim Karani

Reputation: 8886

Small mistake in token 

from nltk.chunk import RegexpParser
grammar = '''
NP: {<DT>?<JJ>*<NN>*}
V: {<V.*>}'''
chunker = RegexpParser(grammar)
token = [] ## Some tokens from my POS tagger
//chunked = chunker.parse(tokens) // token defined in the previous line but used tokens in chunker.parse(tokens)
chunked = chunker.parse(token) // Change in this line
print chunked

Upvotes: 0

Related Questions