def command_bilingual_lexicon(args_):
if args_.random_pair_per_synset:
lexicon = bilingual_lexicon.random_pair_per_synset_bilingual_lexicon(
)
else:
lexicon = bilingual_lexicon.bilingual_lexicon()
for lemma_name_spa, lemma_name_por in lexicon:
print("{} {}".format(lemma_name_spa, lemma_name_por))
def command_linear_trans(args_):
model_es = word_vectors.load_model(args_.model_es_file_name)
model_pt = word_vectors.load_model(args_.model_pt_file_name)
if args_.random_pair_per_synset:
lexicon = bilingual_lexicon.random_pair_per_synset_bilingual_lexicon(
)
elif args_.most_frequent:
lexicon = bilingual_lexicon.most_frequent_bilingual_lexicon_based_on_external_count(
model_es.vocab, model_pt.vocab)
else:
lexicon = bilingual_lexicon.bilingual_lexicon()
X, Y = zip(*word_vectors.bilingual_lexicon_vectors(
model_es, model_pt, bilingual_lexicon=lexicon))
T = linear_trans.linear_transformation(X, Y, args_.backwards)
linear_trans.save_linear_transformation(
args_.translation_matrix_file_name, T)
def command_bilingual_lexicon(_args):
for lemma_name_spa, lemma_name_por in bilingual_lexicon.bilingual_lexicon():
print("{} {}".format(lemma_name_spa, lemma_name_por))
def bilingual_lexicon_vectors(model_es, model_pt):
return ((model_es[word_es], model_pt[word_pt])
for word_es, word_pt in bilingual_lexicon()
if word_es in model_es.vocab and word_pt in model_pt.vocab)
