def getWeightsForQuery(self, query):
indexTf = self.index.getIndex()
words = query.lower().split()
words_stem = []
for w in words:
words_stem.append(porter.stem(w))
resultat = dict()
terms = []
docs = []
docs = indexTf.keys()
for d in docs:
doc = dict()
terms = indexTf[d].keys()
for t in terms:
if t in words_stem:
doc[t] = (1 + np.log(indexTf[d][t])) * np.log(
(1 + len(docs) /
(1 + len(self.index.getTfsForStem(t).keys()))))
else:
doc[t] = 0
resultat[d] = doc
return resultat
def getWeightsForQuery(self, query):
words = query.lower().split()
words_stem = []
for w in words:
words_stem.append(porter.stem(w))
counter = dict(collections.Counter(words_stem))
resultat = dict()
terms = []
indexTf = self.index.getIndex()
docs = []
docs = indexTf.keys()
for d in docs:
doc = dict()
terms = indexTf[d].keys()
for t in terms:
if t in words_stem:
doc[t] = counter[t]
else:
doc[t] = 0
resultat[d] = doc
return resultat
def simple_signature(ambiguous_word, pos=None, lemma=True, stem=False, \
hyperhypo=True, stop=True):
synsets_signatures = {}
for ss in wn.synsets(ambiguous_word):
try:
if pos and str(ss.pos()) != pos:
continue
except:
if pos and str(ss.pos) != pos:
continue
signature = []
ss_definition = synset_properties(ss, 'definition')
signature+=ss_definition
ss_examples = synset_properties(ss, 'examples')
signature+=list(chain(*[i.split() for i in ss_examples]))
ss_lemma_names = synset_properties(ss, 'lemma_names')
signature+= ss_lemma_names
if hyperhypo == True:
ss_hyponyms = synset_properties(ss, 'hyponyms')
ss_hypernyms = synset_properties(ss, 'hypernyms')
ss_hypohypernyms = ss_hypernyms+ss_hyponyms
signature+= list(chain(*[i.lemma_names() for i in ss_hypohypernyms]))
if stop == True:
signature = [i for i in signature if i not in EN_STOPWORDS]
if lemma == True:
signature = [lemmatize(i) for i in signature]
if stem == True:
signature = [porter.stem(i) for i in signature]
synsets_signatures[ss] = signature
return synsets_signatures
def getScores(self,query,pertinence=None):
""" Calcul du score basé sur Okapi-BM25
"""
words=query.lower().split()
words_stem=[]
for w in words:
words_stem.append(porter.stem(w))
index=self.index.getIndex()
index_inverse=self.index.getIndexInverse()
idf={t:self.getIdf(t,index,index_inverse,pertinence) for t in words_stem}
length_docs={doc:sum([int(tf) for tf in index[doc].values()]) for doc in index.keys() }
mean_length_docs=np.mean([int(val) for val in length_docs.values()])
docs=index.keys()
docsScores={}
for d in docs:
score=0
for t in words_stem:
score+=idf[t]*index[d].get(t,0)/(index[d].get(t,0) +self.K1*(1-self.B+self.B*(length_docs[d]/mean_length_docs)))
docsScores[d]=score
return docsScores
def adapted_lesk(context_sentence, ambiguous_word, \
pos=None, lemma=True, stem=True, hyperhypo=True, \
stop=True, context_is_lemmatized=False, \
nbest=False, keepscore=False, normalizescore=False):
"""
This function is the implementation of the Adapted Lesk algorithm,
described in Banerjee and Pederson (2002). It makes use of the lexical
items from semantically related senses within the wordnet
hierarchies and to generate more lexical items for each sense.
see www.d.umn.edu/~tpederse/Pubs/cicling2002-b.pdf
"""
# Ensure that ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word)
# If ambiguous word not in WordNet return None
if not wn.synsets(ambiguous_word):
return None
# Get the signatures for each synset.
ss_sign = simple_signature(ambiguous_word, pos, lemma, stem, hyperhypo)
for ss in ss_sign:
# Includes holonyms.
ss_mem_holonyms = synset_properties(ss, 'member_holonyms')
ss_part_holonyms = synset_properties(ss, 'part_holonyms')
ss_sub_holonyms = synset_properties(ss, 'substance_holonyms')
# Includes meronyms.
ss_mem_meronyms = synset_properties(ss, 'member_meronyms')
ss_part_meronyms = synset_properties(ss, 'part_meronyms')
ss_sub_meronyms = synset_properties(ss, 'substance_meronyms')
# Includes similar_tos
ss_simto = synset_properties(ss, 'similar_tos')
related_senses = list(
set(ss_mem_holonyms + ss_part_holonyms + ss_sub_holonyms +
ss_mem_meronyms + ss_part_meronyms + ss_sub_meronyms +
ss_simto))
signature = list([
j for j in chain(
*[synset_properties(i, 'lemma_names') for i in related_senses])
if j not in EN_STOPWORDS
])
# Lemmatized context is preferred over stemmed context
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Matching exact words causes sparsity, so optional matching for stems.
if stem == True:
signature = [porter.stem(i) for i in signature]
# Adds the extended signature to the simple signatures.
ss_sign[ss] += signature
# Disambiguate the sense in context.
if context_is_lemmatized:
context_sentence = context_sentence.split()
else:
context_sentence = lemmatize_sentence(context_sentence)
best_sense = compare_overlaps(context_sentence, ss_sign, \
nbest=nbest, keepscore=keepscore, \
normalizescore=normalizescore)
return best_sense
def adapted_lesk(context_sentence, ambiguous_word, \
pos=None, lemma=True, stem=True, hyperhypo=True, \
stop=True, context_is_lemmatized=False, \
nbest=False, keepscore=False, normalizescore=False):
"""
This function is the implementation of the Adapted Lesk algorithm,
described in Banerjee and Pederson (2002). It makes use of the lexical
items from semantically related senses within the wordnet
hierarchies and to generate more lexical items for each sense.
see www.d.umn.edu/~tpederse/Pubs/cicling2002-b.pdf
"""
# Ensure that ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word)
# Get the signatures for each synset.
ss_sign = simple_signature(ambiguous_word, pos, lemma, stem, hyperhypo)
for ss in ss_sign:
related_senses = list(set(ss.member_holonyms() + ss.member_meronyms() +
ss.part_meronyms() + ss.part_holonyms() +
ss.similar_tos() + ss.substance_holonyms() +
ss.substance_meronyms()))
try:
signature = list([j for j in chain(*[i.lemma_names() for i in \
related_senses]) if j not in stopwords.words('english')])
except:
signature = list([j for j in chain(*[i.lemma_names for i in \
related_senses]) if j not in stopwords.words('english')])
# Lemmatized context is preferred over stemmed context
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Matching exact words causes sparsity, so optional matching for stems.
if stem == True:
signature = [porter.stem(i) for i in signature]
ss_sign[ss]+=signature
# Disambiguate the sense in context.
if context_is_lemmatized:
context_sentence = [porter.stem(i) for i in context_sentence.split()]
else:
context_sentence = lemmatize_sentence(context_sentence)
best_sense = compare_overlaps(context_sentence, ambiguous_word, ss_sign, \
nbest=nbest, keepscore=keepscore, \
normalizescore=normalizescore)
return best_sense
def adapted_lesk(context_sentence, ambiguous_word, \
pos=None, lemma=True, stem=True, hyperhypo=True, \
stop=True, context_is_lemmatized=False, \
nbest=False, keepscore=False, normalizescore=False):
"""
This function is the implementation of the Adapted Lesk algorithm,
described in Banerjee and Pederson (2002). It makes use of the lexical
items from semantically related senses within the wordnet
hierarchies and to generate more lexical items for each sense.
see www.d.umn.edu/~tpederse/Pubs/cicling2002-b.pdf
"""
# Ensure that ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word)
# If ambiguous word not in WordNet return None
if not wn.synsets(ambiguous_word):
return None
# Get the signatures for each synset.
ss_sign = simple_signature(ambiguous_word, pos, lemma, stem, hyperhypo)
for ss in ss_sign:
# Includes holonyms.
ss_mem_holonyms = synset_properties(ss, 'member_holonyms')
ss_part_holonyms = synset_properties(ss, 'part_holonyms')
ss_sub_holonyms = synset_properties(ss, 'substance_holonyms')
# Includes meronyms.
ss_mem_meronyms = synset_properties(ss, 'member_meronyms')
ss_part_meronyms = synset_properties(ss, 'part_meronyms')
ss_sub_meronyms = synset_properties(ss, 'substance_meronyms')
# Includes similar_tos
ss_simto = synset_properties(ss, 'similar_tos')
related_senses = list(set(ss_mem_holonyms+ss_part_holonyms+
ss_sub_holonyms+ss_mem_meronyms+
ss_part_meronyms+ss_sub_meronyms+ ss_simto))
signature = list([j for j in chain(*[synset_properties(i, 'lemma_names')
for i in related_senses])
if j not in EN_STOPWORDS])
# Lemmatized context is preferred over stemmed context
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Matching exact words causes sparsity, so optional matching for stems.
if stem == True:
signature = [porter.stem(i) for i in signature]
# Adds the extended signature to the simple signatures.
ss_sign[ss]+=signature
# Disambiguate the sense in context.
if context_is_lemmatized:
context_sentence = context_sentence.split()
else:
context_sentence = lemmatize_sentence(context_sentence)
best_sense = compare_overlaps(context_sentence, ss_sign, \
nbest=nbest, keepscore=keepscore, \
normalizescore=normalizescore)
return best_sense
def counter(doc):
"""
Processing d'un document
Args:
- doc : document considéré
Return:
- (mot,occurrence) pour chaque mot présent dans le document
"""
l = [pt.stem(w.lower()) for w in doc.split(" ")]
stemmer = tr.PorterStemmer()
l = [word for word in l if word not in stemmer.stopWords]
return dict(collections.Counter(l).items())
def simple_signature(ambiguous_word, pos=None, lemma=True, stem=False, \
hyperhypo=True, stop=True):
"""
Returns a synsets_signatures dictionary that includes signature words of a
sense from its:
(i) definition
(ii) example sentences
(iii) hypernyms and hyponyms
"""
synsets_signatures = {}
for ss in wn.synsets(ambiguous_word):
# If POS is specified.
try:
if pos and str(ss.pos()) != pos:
continue
except:
if pos and str(ss.pos) != pos:
continue
signature = []
# Includes definition.
try: signature+= ss.definition().split()
except: signature+= ss.definition.split()
# Includes examples
try: signature+= list(chain(*[i.split() for i in ss.examples()]))
except: signature+= list(chain(*[i.split() for i in ss.examples]))
# Includes lemma_names.
try: signature+= ss.lemma_names()
except: signature+= ss.lemma_names
# Optional: includes lemma_names of hypernyms and hyponyms.
if hyperhypo == True:
try: signature+= list(chain(*[i.lemma_names() for i \
in ss.hypernyms()+ss.hyponyms()]))
except: signature+= list(chain(*[i.lemma_names for i \
in ss.hypernyms()+ss.hyponyms()]))
# Optional: removes stopwords.
if stop == True:
signature = [i for i in signature if i not in stopwords.words('english')]
# Lemmatized context is preferred over stemmed context
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Matching exact words causes sparsity, so optional matching for stems.
if stem == True:
signature = [porter.stem(i) for i in signature]
signature = [i.lower() for i in signature]
synsets_signatures[ss] = signature
return synsets_signatures
def getScores(self, query):
weighter=self.getWeighter()
words=query.lower().split()
self.norm_doc={} #Les normes des documents
words_stem=[]
for w in words:
words_stem.append(porter.stem(w))
if(self.normalized): #Methode Cosinus
docs=weighter.getWeightsForQuery(query)
keysDocs=docs.keys()
docsScores={}
for k in keysDocs:
score=0
weighterDoc=weighter.getWeightsForDoc(k)
for stem in words_stem:
if stem in docs[k].keys():
score+=docs[k][stem]*weighterDoc[stem]
norm_vect1=np.linalg.norm(np.array(list(docs[k].values())),ord=2)
if k in self.norm_doc.keys():
norm_vect2=self.norm_doc[k]
else:
norm_vect2=np.linalg.norm(np.array(list(weighterDoc.values())),ord=2)
self.norm_doc[k]=norm_vect2
docsScores[k]=score/(norm_vect1+norm_vect2)
else: #Produit scalaire
docs=weighter.getWeightsForQuery(query)
keysDocs=docs.keys()
docsScores={}
for k in keysDocs:
score=0
weighterDoc=weighter.getWeightsForDoc(k)
for stem in words_stem:
if stem in docs[k].keys():
score+=docs[k][stem]*weighterDoc[stem]
docsScores[k]=score
return docsScores
def cosine_lesk(
context_sentence,
ambiguous_word,
pos=None,
lemma=True,
stem=True,
hyperhypo=True,
stop=True,
context_is_lemmatized=False,
nbest=False,
):
"""
In line with vector space models, we can use cosine to calculate overlaps
instead of using raw overlap counts. Essentially, the idea of using
signatures (aka 'sense paraphrases') is lesk-like.
"""
# Ensure that ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word)
# If ambiguous word not in WordNet return None
if not wn.synsets(ambiguous_word):
return None
synsets_signatures = simple_signature(ambiguous_word, pos, lemma, stem, hyperhypo)
if context_is_lemmatized:
context_sentence = " ".join(context_sentence.split())
else:
context_sentence = " ".join(lemmatize_sentence(context_sentence))
scores = []
for ss, signature in synsets_signatures.items():
# Lowercase and replace "_" with spaces.
signature = " ".join(map(str, signature)).lower().replace("_", " ")
# Removes punctuation.
signature = [i for i in word_tokenize(signature) if i not in string.punctuation]
# Optional: remove stopwords.
if stop:
signature = [i for i in signature if i not in EN_STOPWORDS]
# Optional: Lemmatize the tokens.
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Optional: stem the tokens.
if stem:
signature = [porter.stem(i) for i in signature]
scores.append((cos_sim(context_sentence, " ".join(signature)), ss))
if not nbest:
return sorted(scores, reverse=True)[0][1]
else:
return [(j, i) for i, j in sorted(scores, reverse=True)]
def simple_signature(ambiguous_word, pos=None, lemma=True, stem=False, \
hyperhypo=True, stop=True):
"""
Returns a synsets_signatures dictionary that includes signature words of a
sense from its:
(i) definition
(ii) example sentences
(iii) hypernyms and hyponyms
"""
synsets_signatures = {}
for ss in wn.synsets(ambiguous_word):
try: # If POS is specified.
if pos and str(ss.pos()) != pos:
continue
except:
if pos and str(ss.pos) != pos:
continue
signature = []
# Includes definition.
ss_definition = synset_properties(ss, 'definition')
signature += ss_definition.split()
# Includes examples
ss_examples = synset_properties(ss, 'examples')
signature += list(chain(*[i.split() for i in ss_examples]))
# Includes lemma_names.
ss_lemma_names = synset_properties(ss, 'lemma_names')
signature += ss_lemma_names
# Optional: includes lemma_names of hypernyms and hyponyms.
if hyperhypo == True:
ss_hyponyms = synset_properties(ss, 'hyponyms')
ss_hypernyms = synset_properties(ss, 'hypernyms')
ss_hypohypernyms = ss_hypernyms + ss_hyponyms
signature += list(
chain(*[i.lemma_names() for i in ss_hypohypernyms]))
# Optional: removes stopwords.
if stop == True:
signature = [i for i in signature if i not in EN_STOPWORDS]
# Lemmatized context is preferred over stemmed context.
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Matching exact words may cause sparsity, so optional matching for stems.
if stem == True:
signature = [porter.stem(i) for i in signature]
synsets_signatures[ss] = signature
return synsets_signatures
def simple_signature(ambiguous_word, pos=None, lemma=True, stem=False, \
hyperhypo=True, stop=True):
"""
Returns a synsets_signatures dictionary that includes signature words of a
sense from its:
(i) definition
(ii) example sentences
(iii) hypernyms and hyponyms
"""
synsets_signatures = {}
for ss in wn.synsets(ambiguous_word):
try: # If POS is specified.
if pos and str(ss.pos()) != pos:
continue
except:
if pos and str(ss.pos) != pos:
continue
signature = []
# Includes definition.
ss_definition = synset_properties(ss, 'definition')
signature+=ss_definition
# Includes examples
ss_examples = synset_properties(ss, 'examples')
signature+=list(chain(*[i.split() for i in ss_examples]))
# Includes lemma_names.
ss_lemma_names = synset_properties(ss, 'lemma_names')
signature+= ss_lemma_names
# Optional: includes lemma_names of hypernyms and hyponyms.
if hyperhypo == True:
ss_hyponyms = synset_properties(ss, 'hyponyms')
ss_hypernyms = synset_properties(ss, 'hypernyms')
ss_hypohypernyms = ss_hypernyms+ss_hyponyms
signature+= list(chain(*[i.lemma_names() for i in ss_hypohypernyms]))
# Optional: removes stopwords.
if stop == True:
signature = [i for i in signature if i not in EN_STOPWORDS]
# Lemmatized context is preferred over stemmed context.
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Matching exact words may cause sparsity, so optional matching for stems.
if stem == True:
signature = [porter.stem(i) for i in signature]
synsets_signatures[ss] = signature
return synsets_signatures
def cosine_lesk(context_sentence, ambiguous_word, \
pos=None, lemma=True, stem=True, hyperhypo=True, \
stop=True, context_is_lemmatized=False, \
nbest=False):
"""
In line with vector space models, we can use cosine to calculate overlaps
instead of using raw overlap counts. Essentially, the idea of using
signatures (aka 'sense paraphrases') is lesk-like.
"""
# Ensure that ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word)
# If ambiguous word not in WordNet return None
if not wn.synsets(ambiguous_word):
return None
synsets_signatures = simple_signature(ambiguous_word, pos, lemma, stem,
hyperhypo)
if context_is_lemmatized:
context_sentence = " ".join(context_sentence.split())
else:
context_sentence = " ".join(lemmatize_sentence(context_sentence))
scores = []
for ss, signature in synsets_signatures.items():
# Lowercase and replace "_" with spaces.
signature = " ".join(map(str, signature)).lower().replace("_", " ")
# Removes punctuation.
signature = [i for i in word_tokenize(signature) \
if i not in string.punctuation]
# Optional: remove stopwords.
if stop:
signature = [i for i in signature if i not in EN_STOPWORDS]
# Optional: Lemmatize the tokens.
if lemma == True:
signature = [lemmatize(i) for i in signature]
# Optional: stem the tokens.
if stem:
signature = [porter.stem(i) for i in signature]
scores.append((cos_sim(context_sentence, " ".join(signature)), ss))
if not nbest:
return sorted(scores, reverse=True)[0][1]
else:
return [(j, i) for i, j in sorted(scores, reverse=True)]
def adapted_lesk(context_sentence, ambiguous_word, \
pos=None, lemma=True, stem=True, hyperhypo=True, \
stop=True, context_is_lemmatized=False, \
nbest=False, keepscore=False, normalizescore=False):
# Ensure ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word)
# If ambiguous word not in WordNet return None
if not wn.synsets(ambiguous_word):
return None
ss_sign = simple_signature(ambiguous_word, pos, lemma, stem, hyperhypo)
for ss in ss_sign:
ss_mem_holonyms = synset_properties(ss, 'member_holonyms')
ss_part_holonyms = synset_properties(ss, 'part_holonyms')
ss_sub_holonyms = synset_properties(ss, 'substance_holonyms')
ss_mem_meronyms = synset_properties(ss, 'member_meronyms')
ss_part_meronyms = synset_properties(ss, 'part_meronyms')
ss_sub_meronyms = synset_properties(ss, 'substance_meronyms')
ss_simto = synset_properties(ss, 'similar_tos')
related_senses = list(set(ss_mem_holonyms+ss_part_holonyms+
ss_sub_holonyms+ss_mem_meronyms+
ss_part_meronyms+ss_sub_meronyms+ ss_simto))
signature = list([j for j in chain(*[synset_properties(i, 'lemma_names')
for i in related_senses])
if j not in EN_STOPWORDS])
if lemma == True:
signature = [lemmatize(i) for i in signature]
#if stem == True:
signature = [porter.stem(i) for i in signature]
ss_sign[ss]+=signature
if context_is_lemmatized:
context_sentence = context_sentence.split()
else:
context_sentence = lemmatize_sentence(context_sentence)
best_sense = compare_overlaps(context_sentence, ss_sign, \
nbest=nbest, keepscore=keepscore, \
normalizescore=normalizescore)
return best_sense
def simple_lesk(context_sentence, ambiguous_word, \
pos=None, lemma=True, stem=False, hyperhypo=True, \
stop=True, context_is_lemmatized=False, \
nbest=False, keepscore=False, normalizescore=False):
"""
Simple Lesk is somewhere in between using more than the
original Lesk algorithm (1986) and using less signature
words than adapted Lesk (Banerjee and Pederson, 2002)
"""
# Ensure that ambiguous word is a lemma.
ambiguous_word = lemmatize(ambiguous_word).lower()
# Get the signatures for each synset.
ss_sign = simple_signature(ambiguous_word, pos, lemma, stem, hyperhypo)
# Disambiguate the sense in context.
if context_is_lemmatized:
context_sentence = [porter.stem(i.lower()) for i in context_sentence.split()]
else:
context_sentence = lemmatize_sentence(context_sentence)
best_sense = compare_overlaps(context_sentence, ambiguous_word, ss_sign, \
nbest=nbest, keepscore=keepscore, \
normalizescore=normalizescore)
return best_sense
def getScores(self, query):
"""
Parameters
----------
query : String
Returns Les scores des documents sous forme de couple (Doc , Score) dans un dict
Calcul du score basé sur Le lissage Jelineck-Mercer
-------
"""
words=query.lower().split()
words_stem=[]
for w in words:
words_stem.append(porter.stem(w))
index=self.index.getIndex()
docs=index.keys()
docsScores={}
probaCollection={}
sizeOfCollection=self.index.getCollectionSize()
for t in words_stem:
probaCollection[t]=sum([doc.get(t,0) for doc in index.values()])/sizeOfCollection
for d in docs:
score=1
for t in words_stem:
score*=(1-self.lambda_)*index[d].get(t,0) + self.lambda_*probaCollection[t]
docsScores[d]=score
return docsScores
