def main():
logging.basicConfig(level=logging.INFO, format='%(message)s')
parser = argparse.ArgumentParser(description='Train alignment model')
parser.add_argument('--train', help='training corpus', required=True)
parser.add_argument('--iter',
help='number of iterations',
type=int,
required=True)
parser.add_argument('--charlm', help='character language model')
parser.add_argument('--pyp',
help='G_w^0 is PYP(CharLM)',
action='store_true')
parser.add_argument('--output', help='model output path')
parser.add_argument(
'--reverse',
help='train model in reverse direction (but output f-e)',
action='store_true')
args = parser.parse_args()
source_vocabulary = Vocabulary()
source_vocabulary[NULL]
target_vocabulary = Vocabulary()
logging.info('Reading parallel training data')
with open(args.train) as train:
training_corpus = read_parallel_corpus(train, source_vocabulary,
target_vocabulary, args.reverse)
if args.charlm:
logging.info('Preloading character language model')
if args.charlm == 'pu':
char_lm = PoissonUniformCharLM(target_vocabulary)
else:
char_lm = CharLM(args.charlm, target_vocabulary)
if args.pyp:
t_base = PYP(char_lm, PYPPrior(1.0, 1.0, 1.0, 1.0, 0.1, 1.0))
else:
t_base = char_lm
else:
t_base = Uniform(len(target_vocabulary))
model = AlignmentModel(len(source_vocabulary), t_base)
logging.info('Training alignment model')
alignments = run_sampler(model, training_corpus, args.iter)
if args.output:
with open(args.output, 'w') as f:
model.source_vocabulary = source_vocabulary
model.target_vocabulary = target_vocabulary
cPickle.dump(model, f, protocol=-1)
fmt = ('{e}-{f}' if args.reverse else '{f}-{e}')
for a, (f, e) in izip(alignments, training_corpus):
#f_sentence = ' '.join(source_vocabulary[w] for w in f[1:])
#e_sentence = ' '.join(target_vocabulary[w] for w in e)
print(' '.join(
fmt.format(f=j - 1, e=i) for i, j in enumerate(a) if j > 0))
def main():
logging.basicConfig(level=logging.INFO, format='%(message)s')
parser = argparse.ArgumentParser(description='Train alignment model')
parser.add_argument('--train', help='training corpus', required=True)
parser.add_argument('--iter', help='number of iterations', type=int, required=True)
parser.add_argument('--charlm', help='character language model')
parser.add_argument('--pyp', help='G_w^0 is PYP(CharLM)', action='store_true')
parser.add_argument('--output', help='model output path')
parser.add_argument('--reverse', help='train model in reverse direction (but output f-e)',
action='store_true')
args = parser.parse_args()
source_vocabulary = Vocabulary()
source_vocabulary[NULL]
target_vocabulary = Vocabulary()
logging.info('Reading parallel training data')
with open(args.train) as train:
training_corpus = read_parallel_corpus(train, source_vocabulary, target_vocabulary,
args.reverse)
if args.charlm:
logging.info('Preloading character language model')
if args.charlm == 'pu':
char_lm = PoissonUniformCharLM(target_vocabulary)
else:
char_lm = CharLM(args.charlm, target_vocabulary)
if args.pyp:
t_base = PYP(char_lm, PYPPrior(1.0, 1.0, 1.0, 1.0, 0.1, 1.0))
else:
t_base = char_lm
else:
t_base = Uniform(len(target_vocabulary))
model = AlignmentModel(len(source_vocabulary), t_base)
logging.info('Training alignment model')
alignments = run_sampler(model, training_corpus, args.iter)
if args.output:
with open(args.output, 'w') as f:
model.source_vocabulary = source_vocabulary
model.target_vocabulary = target_vocabulary
cPickle.dump(model, f, protocol=-1)
fmt = ('{e}-{f}' if args.reverse else '{f}-{e}')
for a, (f, e) in izip(alignments, training_corpus):
#f_sentence = ' '.join(source_vocabulary[w] for w in f[1:])
#e_sentence = ' '.join(target_vocabulary[w] for w in e)
print(' '.join(fmt.format(f=j-1, e=i) for i, j in enumerate(a) if j > 0))
