这是一种启发式方法。我刚刚对其进行了编码,以便为样式使用代码。它使用来自wordnet的derivationally_related_forms()。我已经实现名词化。我猜verbify工作类似。根据我的测试,效果很好:
from nltk.corpus import wordnet as wn
def nounify(verb_word):
""" Transform a verb to the closest noun: die -> death """
verb_synsets = wn.synsets(verb_word, pos="v")
# Word not found
if not verb_synsets:
return []
# Get all verb lemmas of the word
verb_lemmas = [l for s in verb_synsets \
for l in s.lemmas if s.name.split('.')[1] == 'v']
# Get related forms
derivationally_related_forms = [(l, l.derivationally_related_forms()) \
for l in verb_lemmas]
# filter only the nouns
related_noun_lemmas = [l for drf in derivationally_related_forms \
for l in drf[1] if l.synset.name.split('.')[1] == 'n']
# Extract the words from the lemmas
words = [l.name for l in related_noun_lemmas]
len_words = len(words)
# Build the result in the form of a list containing tuples (word, probability)
result = [(w, float(words.count(w))/len_words) for w in set(words)]
result.sort(key=lambda w: -w[1])
# return all the possibilities sorted by probability
return result