Esempio n. 1
0
    return word_vect_matrix


source_language = 'spanish'
target_language = 'english07'
pair_filename = 'word_pairs/es-en.pair'
reverse_pair = False

target_vectors, target_vect_size = word_vect_loader.load('pos_data/'+target_language+'.train.sent.vec')
source_vectors, source_vect_size = word_vect_loader.load('pos_data/'+source_language+'.train.sent.vec')
assert source_vect_size == target_vect_size
vect_size = source_vect_size

print 'loading'
source_text_sentences = load_and_save.read_sentences_from_file('pos_data/conll-'+source_language+'.pos')
source_sentences, source_words, source_sentences_pos, _ = load_and_save.integer_sentences(source_text_sentences, pos=universal_pos_tags, max_words=10000)
source_test_sentences = load_and_save.read_sentences_from_file('pos_data/conll-'+source_language+'-test.pos')
source_test_sentences, _, source_test_sentences_pos, _ = load_and_save.integer_sentences(source_test_sentences, pos=universal_pos_tags, words=source_words)

target_text_sentences = load_and_save.read_sentences_from_file('pos_data/conll-'+target_language+'-test.pos')
target_sentences, target_words, target_sentences_pos, _ = load_and_save.integer_sentences(target_text_sentences, pos=universal_pos_tags, max_words=10000)

source_vector_matrix = make_vector_matrix(source_words, source_vectors, vect_size)
target_vector_matrix = make_vector_matrix(target_words, target_vectors, vect_size)

print 'finding rotation'
translation_pairs = []
pair_file = open(pair_filename)
for line in pair_file:
    split = line.split()
    if split[0] in source_words and split[2] in target_words: