word_pairs = nlp.read_csv(CSV_DIR + CSV_NAME)
print "CSV", CSV_NAME
vocab = []
for p in word_pairs:
vocab.append(p[0].lower())
vocab.append(p[1].lower())
vocab = list(set(vocab))
for w in vocab:
word_hypernyms[w] = nlp.read_hypernyms(w)
word_hyponyms[w] = nlp.read_hyponyms(w)
word_synonyms[w] = nlp.read_synonyms(w)
senses[w] = nlp.read_senses(w)
for s in senses[w]:
sense_vectors[s] = np.zeros(VECTOR_DIM)
sense_hypernyms[s] = nlp.read_hypernyms_by_sense(s)
sense_hyponyms[s] = nlp.read_hyponyms_by_sense(s)
sense_synonyms[s] = nlp.read_synonyms_by_sense(s)
sense_pool[s] = nlp.get_pooling(s, sense_hypernyms, sense_synonyms,
sense_hyponyms, word_vectors,
VECTOR_DIM)
if (word_vectors.has_key(w)):
sense_pool[s] = sense_pool[s] + word_vectors[w]
sense_vectors[s] = sense_pool[s]
for l in s.lemmas():
word = str(l.name())
word_hypernyms[word] = nlp.read_hypernyms(word)
word_hyponyms[word] = nlp.read_hyponyms(word)
word_synonyms[word] = nlp.read_synonyms(word)
word_pool[word] = nlp.get_pooling(word, word_hypernyms,
word_synonyms, word_hyponyms,
word_vectors, VECTOR_DIM)
else:
continue
if ( m_score > 0.0 ):
machine_score.append(m_score)
human_score.append(float(p[2]))
p_val, p_rel = sci.stats.spearmanr(human_score, machine_score)
print "Simple Linear Approach", p_val
if __name__ == "__main__":
word_vectors = nlp.read_word_vectors(VECTOR_DIR + VECTOR_NAME)
word_pairs = nlp.read_csv(CSV_DIR + CSV_NAME)
vocab = []
for p in word_pairs:
vocab.append(p[0].lower())
vocab.append(p[1].lower())
vocab = list(set(vocab))
for w in vocab:
word_hypernyms[w] = nlp.read_hypernyms(w)
word_hyponyms[w] = nlp.read_hyponyms(w)
word_synonyms[w] = nlp.read_synonyms(w)
senses[w] = nlp.read_senses(w)
for s in senses[w]:
sense_vectors[s] = np.zeros(VECTOR_DIM)
sense_hypernyms[s] = nlp.read_hypernyms_by_sense(s)
sense_hyponyms[s] = nlp.read_hyponyms_by_sense(s)
sense_synonyms[s] = nlp.read_synonyms_by_sense(s)
sense_vectors[s] = nlp.get_pooling(s, sense_hypernyms,sense_synonyms,sense_hyponyms, word_vectors, VECTOR_DIM)
if ( word_vectors.has_key(w)):
sense_vectors[s] = sense_vectors[s] + word_vectors[w]
word_pool[w] = nlp.get_pooling(w, word_hypernyms, word_synonyms, word_hyponyms, word_vectors, VECTOR_DIM)
test_sense_vectors()
if __name__ == "__main__":
word_pairs = nlp_lib.read_csv( CSV_DIR + CSV_NAME )
for w_pair in word_pairs:
vocab.append( w_pair[0].lower() )
vocab.append( w_pair[1].lower() )
#remove duplicated words in csv file
vocab = list(set(vocab))
word_vectors = nlp_lib.read_word_vectors(VECTOR_DIR + VECTOR_NAME)
#read word senses
for w in vocab:
word_senses[w] = nlp_lib.read_senses(w)
#read word senses' hyponyms
for w in vocab:
for s in word_senses[w]:
word_sense_hyponyms[s] = nlp_lib.read_hyponyms_by_sense(s)
word_sense_hypernyms[s] = nlp_lib.read_hypernyms_by_sense(s)
word_sense_synonyms[s] = nlp_lib.read_synonyms_by_sense(s)
word_sense_full_pooling[s] = get_full_pooling_sense(s, w)
#read for retrofitting
for w in vocab:
word_hyponyms[w] = nlp_lib.read_hyponyms(w)
word_hypernyms[w] = nlp_lib.read_hypernyms(w)
word_synonyms[w] = nlp_lib.read_synonyms(w)
for w in vocab:
print "word",w
if ( word_vectors.has_key(w) ):
print "has a vector"
else:
print "no vector for it"
