def synsetSignatures(ss: "wn.Synset"):
signature = []
# Adds the definition, example sentences and lemma_names.
signature += word_tokenize(ss.definition())
signature += chain(*[word_tokenize(eg) for eg in ss.examples()])
signature += ss.lemma_names()
# Includes lemma_names of hyper-/hyponyms.
hyperhyponyms = set(ss.hyponyms() + ss.hypernyms() +
ss.instance_hyponyms() + ss.instance_hypernyms())
signature += set(chain(*[i.lemma_names() for i in hyperhyponyms]))
# Includes signatures from related senses as in Adapted Lesk.
# Includes lemma_names from holonyms, meronyms and similar_tos
related_senses = set(ss.member_holonyms() + ss.part_holonyms() + ss.substance_holonyms() + \
ss.member_meronyms() + ss.part_meronyms() + ss.substance_meronyms() + \
ss.similar_tos())
signature += set(chain(*[i.lemma_names() for i in related_senses]))
# Lowercase.
signature = set(s.lower() for s in signature)
# Removes stopwords.
signature = set(signature).difference(EN_STOPWORDS)
# Lemmatized context is preferred over stemmed context.
signature = [lemmatize(s) for s in signature]
# Keep only the unique bag-of-words
return set(signature)
def max_similarity(context_sentence: str, ambiguous_word: str, option="path",
lemma=True, context_is_lemmatized=False, pos=None, best=True) -> "wn.Synset":
"""
Perform WSD by maximizing the sum of maximum similarity between possible
synsets of all words in the context sentence and the possible synsets of the
ambiguous words (see http://goo.gl/XMq2BI):
{argmax}_{synset(a)}(\sum_{i}^{n}{{max}_{synset(i)}(sim(i,a))}
:param context_sentence: String, a sentence.
:param ambiguous_word: String, a single word.
:return: If best, returns only the best Synset, else returns a dict.
"""
ambiguous_word = lemmatize(ambiguous_word)
# If ambiguous word not in WordNet return None
if not wn.synsets(ambiguous_word):
return None
if context_is_lemmatized:
context_sentence = word_tokenize(context_sentence)
else:
context_sentence = [lemmatize(w) for w in word_tokenize(context_sentence)]
result = {}
for i in wn.synsets(ambiguous_word, pos=pos):
result[i] = 0
for j in context_sentence:
_result = [0]
for k in wn.synsets(j):
_result.append(sim(i,k,option))
result[i] += max(_result)
if option in ["res","resnik"]: # lower score = more similar
result = sorted([(v,k) for k,v in result.items()])
else: # higher score = more similar
result = sorted([(v,k) for k,v in result.items()],reverse=True)
return result[0][1] if best else result
def synset_signatures(ss,
hyperhypo=True,
adapted=False,
remove_stopwords=True,
to_lemmatize=True,
remove_numbers=True,
lowercase=True,
original_lesk=False,
from_cache=True):
"""
:param ss: A WordNet synset.
:type ss: nltk.corpus.wordnet.Synset
"""
if from_cache:
return synset_signatures_from_cache(ss, hyperhypo, adapted,
original_lesk)
# Collects the signatures from WordNet.
signature = []
# Adds the definition, example sentences and lemma_names.
signature += word_tokenize(ss.definition())
# If the original lesk signature is requested, skip the other signatures.
if original_lesk:
return set(signature)
# Adds the examples and lemma names.
signature += chain(*[word_tokenize(eg) for eg in ss.examples()])
signature += ss.lemma_names()
# Includes lemma_names of hyper-/hyponyms.
if hyperhypo:
hyperhyponyms = set(ss.hyponyms() + ss.hypernyms() +
ss.instance_hyponyms() + ss.instance_hypernyms())
signature += set(chain(*[i.lemma_names() for i in hyperhyponyms]))
# Includes signatures from related senses as in Adapted Lesk.
if adapted:
# Includes lemma_names from holonyms, meronyms and similar_tos
related_senses = set(ss.member_holonyms() + ss.part_holonyms() + ss.substance_holonyms() + \
ss.member_meronyms() + ss.part_meronyms() + ss.substance_meronyms() + \
ss.similar_tos())
signature += set(chain(*[i.lemma_names() for i in related_senses]))
# Lowercase.
signature = set(s.lower() for s in signature) if lowercase else signature
# Removes stopwords.
signature = set(signature).difference(
EN_STOPWORDS) if remove_stopwords else signature
# Lemmatized context is preferred over stemmed context.
if to_lemmatize:
signature = [
lemmatize(s)
if lowercase else lemmatize(s) # Lowercasing checks here.
for s in signature
# We only throw away if both remove_numbers and s is a digit are true.
if not (remove_numbers and s.isdigit())
]
# Keep only the unique bag-of-words
return set(signature)