Mar-24-2017, 05:38 PM
HII,
How to extract only NP TAG from the below tree.
i need this only e.g (NP Electrical/JJ power/NN)
How to extract only NP TAG from the below tree.
i need this only e.g (NP Electrical/JJ power/NN)
toks = nltk.word_tokenize(line) postoks = nltk.tag.pos_tag(toks) grammar= r""" NP:{<JJ>*<NN.*>+} """ chunker = nltk.RegexpParser(grammar) tree= chunker.parse(postoks)
Output:(S
(NP Electrical/JJ power/NN)
can/MD
be/VB
generated/VBN
by/IN
(NP means/NNS)
of/IN
(NP nuclear/JJ power/NN)
./.
In/IN
(NP nuclear/JJ power/NN station/NN)
,/,
(NP electrical/JJ power/NN)
is/VBZ
generated/VBN
by/IN
(NP nuclear/JJ reaction/NN)
./.
Here/RB
,/,
(NP heavy/JJ radioactive/JJ elements/NNS such/JJ)
as/IN
(NP Uranium/NNP)
(/(
(NP U235/NNP)
)/)
or/CC
(NP Thorium/NNP)
(/(
(NP Th232/NNP)
)/)
are/VBP
subjected/VBN
to/TO
(NP nuclear/JJ fission/NN)
./.
This/DT
(NP fission/NN)
is/VBZ
done/VBN
in/IN
a/DT
(NP special/JJ apparatus/NN)
called/VBN
as/IN
(NP reactor/NN)
./.)