I'm trying to get the noun from a verb with Wordnet in python.
I want to be able to get :
from the verb 'created' the noun 'creator',
'funded' => 'funder'
Verb X => Noun Y
Y
is referring to a person
I've been able to do it the other side : Noun Y => Verb X
import nltk as nltk
from nltk.corpus import wordnet as wn
lem = wn.lemmas('creation')
print lem
related_forms = lem[0].derivationally_related_forms()
print related_forms
Here is the output given
[Lemma('creation.n.01.creation'), Lemma('creation.n.02.creation'), Lemma('creation.n.03.creation'), Lemma('initiation.n.02.creation'), Lemma('creation.n.05.Creation'), Lemma('universe.n.01.creation')]
[Lemma('create.v.02.create'), Lemma('produce.v.02.create'), Lemma('create.v.03.create')]
But, I'm trying to do the opposite.
Here is a link that looks like what I want to do, but the code is not working and doesn't answer my request:
Convert words between verb/noun/adjective forms
You could try something like this:
def nounify(verb_word):
set_of_related_nouns = set()
for lemma in wn.lemmas(wn.morphy(verb_word, wn.VERB), pos="v"):
for related_form in lemma.derivationally_related_forms():
for synset in wn.synsets(related_form.name(), pos=wn.NOUN):
if wn.synset('person.n.01') in synset.closure(lambda s:s.hypernyms()):
set_of_related_nouns.add(synset)
return set_of_related_nouns
This method looks up all derivationally related nouns to a verb, and checks if they have "person" as a hypernym.
This input
print nounify("created")
print nounify("teach")
print nounify("spoke")
will return this output
set([Synset('creator.n.02'), Synset('creature.n.02'), Synset('creature.n.03')])
set([Synset('teacher.n.01')])
set([Synset('speaker.n.03'), Synset('speaker.n.01')])
Unfortunately, however, your "fund" example isn't covered, as "funder" isn't listed as a derivationally related form to "fund" in WordNet.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With