def _make_training_folder(self, bilingual_corpora, monolingual_corpora, domains, folder):
for corpus in bilingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(domains[corpus.name], folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
for corpus in monolingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
return BilingualCorpus.splitlist(self._source_lang, self._target_lang, roots=folder)
def _make_training_folder(self, bilingual_corpora, monolingual_corpora, domains, folder):
for corpus in bilingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(domains[corpus.name], folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
for corpus in monolingual_corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, folder, corpus.langs)
for lang in corpus.langs:
os.symlink(corpus.get_file(lang), dest_corpus.get_file(lang))
return BilingualCorpus.splitlist(self._source_lang, self._target_lang, roots=folder)
def build(self, corpora, working_dir='.', log_file=None):
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
merged_corpus = BilingualCorpus.make_parallel('merge', working_dir, (self._source_lang, self._target_lang))
fileutils.merge([corpus.get_file(self._source_lang) for corpus in corpora],
merged_corpus.get_file(self._source_lang))
fileutils.merge([corpus.get_file(self._target_lang) for corpus in corpora],
merged_corpus.get_file(self._target_lang))
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Train model
command = [self._build_bin,
'-s', merged_corpus.get_file(self._source_lang), '-t', merged_corpus.get_file(self._target_lang),
'-m', self._model, '-I', '4']
shell.execute(command, stderr=log)
finally:
if log_file is not None:
log.close()
def train(self, corpora, aligner, working_dir='.', log_file=None):
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, working_dir,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file, dest_corpus.get_file(self._source_lang))
os.symlink(target_file, dest_corpus.get_file(self._target_lang))
aligner.align(corpus, os.path.join(working_dir, corpus.name + '.align'))
# Build models
command = [self._build_bin, '--input', working_dir, '--model', self._model,
'-s', self._source_lang, '-t', self._target_lang]
shell.execute(command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def build(self, corpora, working_dir='.', log_file=None):
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
merged_corpus = BilingualCorpus.make_parallel(
'merge', working_dir, (self._source_lang, self._target_lang))
fileutils.merge(
[corpus.get_file(self._source_lang) for corpus in corpora],
merged_corpus.get_file(self._source_lang))
fileutils.merge(
[corpus.get_file(self._target_lang) for corpus in corpora],
merged_corpus.get_file(self._target_lang))
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Train model
command = [
self._build_bin, '-s',
merged_corpus.get_file(self._source_lang), '-t',
merged_corpus.get_file(self._target_lang), '-m', self._model,
'-I', '4'
]
shell.execute(command, stderr=log)
finally:
if log_file is not None:
log.close()
def train(self, corpora, aligner, working_dir='.', log=None):
if log is None:
log = shell.DEVNULL
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
train_corpora = [] # Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, working_dir,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file, dest_corpus.get_file(self._source_lang))
os.symlink(target_file, dest_corpus.get_file(self._target_lang))
train_corpora.append(dest_corpus)
# Align corpora
aligner.align(train_corpora, working_dir, log=log)
# Build models
command = [self._build_bin, '--input', working_dir, '--model', self._model,
'-s', self._source_lang, '-t', self._target_lang]
shell.execute(command, stdout=log, stderr=log)
def build(self, corpora, working_dir='.', log=None):
if log is None:
log = shell.DEVNULL
shutil.rmtree(self._model, ignore_errors=True)
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
merged_corpus = BilingualCorpus.make_parallel(
'merge', working_dir, (self._source_lang, self._target_lang))
fileutils.merge(
[corpus.get_file(self._source_lang) for corpus in corpora],
merged_corpus.get_file(self._source_lang))
fileutils.merge(
[corpus.get_file(self._target_lang) for corpus in corpora],
merged_corpus.get_file(self._target_lang))
command = [
self._build_bin, '-s',
merged_corpus.get_file(self._source_lang), '-t',
merged_corpus.get_file(self._target_lang), '-m', self._model, '-I',
'4'
]
shell.execute(command, stdout=log, stderr=log)
def process(self, corpora, dest_folder, print_tags=True, print_placeholders=False, original_spacing=False):
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang])
self.__process_file(source, dest, lang, print_tags, print_placeholders, original_spacing)
return BilingualCorpus.list(dest_folder)
def process_corpora(self, corpora, dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang])
self.process_file(source, dest, lang)
return BilingualCorpus.list(dest_folder)
def process_corpora(self, corpora, dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang])
self.process_file(source, dest, lang)
return BilingualCorpus.list(dest_folder)
def encode(self, corpora, dest_folder):
if not os.path.isdir(dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest_file = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang]).get_file(lang)
self.encode_file(source, dest_file, delete_nl=True)
return BilingualCorpus.list(dest_folder)
def encode(self, corpora, dest_folder):
if not os.path.isdir(dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest_file = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang]).get_file(lang)
self.encode_file(source, dest_file, delete_nl=True)
return BilingualCorpus.list(dest_folder)
def train(self, corpora, aligner, working_dir='.', log_file=None):
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(
corpus.name, working_dir,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file,
dest_corpus.get_file(self._source_lang))
os.symlink(target_file,
dest_corpus.get_file(self._target_lang))
aligner.align(
corpus, os.path.join(working_dir, corpus.name + '.align'))
# Build models
command = [
self._build_bin, '--input', working_dir, '--model',
self._model, '-s', self._source_lang, '-t', self._target_lang
]
shell.execute(command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def train(self, corpora, aligner, working_dir='.', log_file=None):
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
l1 = self._source_lang
l2 = self._target_lang
langs = (l1, l2)
langs_suffix = l1 + '-' + l2
mct_base = self._get_model_basename()
dmp_file = mct_base + '.dmp'
mam_file = mct_base + '.' + langs_suffix + '.mam'
lex_file = mct_base + '.' + langs_suffix + '.lex'
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Clean corpus for training
clean_output = os.path.join(working_dir, 'clean_corpora')
fileutils.makedirs(clean_output, exist_ok=True)
corpora = self._cleaner.clean(corpora, clean_output, (self._source_lang, self._target_lang))
# Create merged corpus and domains list file (dmp)
merged_corpus = BilingualCorpus.make_parallel(os.path.basename(mct_base), working_dir, langs)
fileutils.merge([corpus.get_file(l1) for corpus in corpora], merged_corpus.get_file(l1))
fileutils.merge([corpus.get_file(l2) for corpus in corpora], merged_corpus.get_file(l2))
with open(dmp_file, 'w') as dmp:
for corpus in corpora:
dmp.write(str(corpus.name) + ' ' + str(corpus.count_lines()) + '\n')
# Create alignments in 'bal' file and symmetrize
bal_file = aligner.align(merged_corpus, langs, self._model, working_dir, log_file)
symal_file = os.path.join(working_dir, 'alignments.' + langs_suffix + '.symal')
symal_command = [self._symal_bin, '-a=g', '-d=yes', '-f=yes', '-b=yes']
with open(bal_file) as stdin:
with open(symal_file, 'w') as stdout:
shell.execute(symal_command, stdin=stdin, stdout=stdout, stderr=log)
# Execute mtt-build
mttbuild_command = self._get_mttbuild_command(mct_base, dmp_file, l1)
with open(merged_corpus.get_file(l1)) as stdin:
shell.execute(mttbuild_command, stdin=stdin, stdout=log, stderr=log)
mttbuild_command = self._get_mttbuild_command(mct_base, dmp_file, l2)
with open(merged_corpus.get_file(l2)) as stdin:
shell.execute(mttbuild_command, stdin=stdin, stdout=log, stderr=log)
# Create 'mam' file
mam_command = [self._symal2mam_bin, mam_file]
with open(symal_file) as stdin:
shell.execute(mam_command, stdin=stdin, stdout=log, stderr=log)
# Create 'lex' file
lex_command = [self._mmlexbuild_bin, mct_base + '.', l1, l2, '-o', lex_file]
shell.execute(lex_command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def tune(self,
corpora=None,
debug=False,
context_enabled=True,
random_seeds=False,
max_iterations=25,
early_stopping_value=None):
if corpora is None:
corpora = BilingualCorpus.list(
os.path.join(self.engine.data_path,
TrainingPreprocessor.DEV_FOLDER_NAME))
target_lang = self.engine.target_lang
source_lang = self.engine.source_lang
corpora = [
corpus for corpus in corpora
if source_lang in corpus.langs and target_lang in corpus.langs
]
if len(corpora) == 0:
raise IllegalArgumentException(
'No %s > %s corpora found into specified path' %
(source_lang, target_lang))
source_corpora = [
BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(),
[source_lang]) for corpus in corpora
]
reference_corpora = [
BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(),
[target_lang]) for corpus in corpora
]
cmdlogger = _tuning_logger(4)
cmdlogger.start(self, corpora)
working_dir = self.engine.get_tempdir('tuning')
mert_wd = os.path.join(working_dir, 'mert')
try:
# Tokenization
tokenizer = Tokenizer(target_lang)
tokenized_output = os.path.join(working_dir, 'reference_corpora')
fileutils.makedirs(tokenized_output, exist_ok=True)
with cmdlogger.step('Corpora tokenization') as _:
reference_corpora = tokenizer.process_corpora(
reference_corpora, tokenized_output)
# Create merged corpus
with cmdlogger.step('Merging corpus') as _:
# source
source_merged_corpus = os.path.join(working_dir,
'corpus.' + source_lang)
with open(source_merged_corpus, 'wb') as out:
for corpus in source_corpora:
out.write(corpus.get_file(source_lang) + '\n')
# target
target_merged_corpus = os.path.join(working_dir,
'corpus.' + target_lang)
fileutils.merge([
corpus.get_file(target_lang)
for corpus in reference_corpora
], target_merged_corpus)
# Run MERT algorithm
with cmdlogger.step('Tuning') as _:
# Start MERT
decoder_flags = ['--port', str(self.api.port)]
if self.api.root is not None:
decoder_flags += ['--root', self.api.root]
if not context_enabled:
decoder_flags.append('--skip-context-analysis')
decoder_flags.append('1')
fileutils.makedirs(mert_wd, exist_ok=True)
with tempfile.NamedTemporaryFile() as runtime_moses_ini:
command = [
self._mert_script, source_merged_corpus,
target_merged_corpus, self._mert_i_script,
runtime_moses_ini.name, '--threads',
str(multiprocessing.cpu_count()), '--mertdir',
cli.BIN_DIR, '--mertargs',
'\'--binary --sctype BLEU\'', '--working-dir', mert_wd,
'--nbest', '100', '--decoder-flags',
'"' + ' '.join(decoder_flags) + '"', '--nonorm',
'--closest', '--no-filter-phrase-table'
]
if early_stopping_value is not None:
command += [
'--bleuscorer', self._scorer_script,
'--bleuscorer-flags "-nt" --early-stopping-value %d'
% early_stopping_value
]
if not random_seeds:
command.append('--predictable-seeds')
if max_iterations > 0:
command.append('--maximum-iterations={num}'.format(
num=max_iterations))
with open(self.engine.get_logfile('mert'), 'wb') as log:
shell.execute(' '.join(command),
stdout=log,
stderr=log)
# Read optimized configuration
with cmdlogger.step('Applying changes') as _:
bleu_score = 0
weights = {}
found_weights = False
with open(os.path.join(mert_wd, 'moses.ini')) as moses_ini:
for line in moses_ini:
line = line.strip()
if len(line) == 0:
continue
elif found_weights:
tokens = line.split()
weights[tokens[0].rstrip('=')] = [
float(val) for val in tokens[1:]
]
elif line.startswith('# BLEU'):
bleu_score = float(line.split()[2])
elif line == '[weight]':
found_weights = True
_ = self.api.update_features(weights)
cmdlogger.completed(bleu_score)
finally:
if not debug:
self.engine.clear_tempdir("tuning")
def tune(self, corpora=None, debug=False, context_enabled=True, random_seeds=False, max_iterations=25):
if corpora is None:
corpora = BilingualCorpus.list(os.path.join(self.engine.data_path, TrainingPreprocessor.DEV_FOLDER_NAME))
if len(corpora) == 0:
raise IllegalArgumentException('empty corpora')
if not self.is_running():
raise IllegalStateException('No MMT Server running, start the engine first')
tokenizer = Tokenizer()
target_lang = self.engine.target_lang
source_lang = self.engine.source_lang
source_corpora = [BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(), [source_lang])
for corpus in corpora]
reference_corpora = [BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(), [target_lang])
for corpus in corpora]
cmdlogger = _tuning_logger(4)
cmdlogger.start(self, corpora)
working_dir = self.engine.get_tempdir('tuning')
mert_wd = os.path.join(working_dir, 'mert')
try:
# Tokenization
tokenized_output = os.path.join(working_dir, 'reference_corpora')
fileutils.makedirs(tokenized_output, exist_ok=True)
with cmdlogger.step('Corpora tokenization') as _:
reference_corpora = tokenizer.process_corpora(reference_corpora, tokenized_output)
# Create merged corpus
with cmdlogger.step('Merging corpus') as _:
# source
source_merged_corpus = os.path.join(working_dir, 'corpus.' + source_lang)
with open(source_merged_corpus, 'wb') as out:
for corpus in source_corpora:
out.write(corpus.get_file(source_lang) + '\n')
# target
target_merged_corpus = os.path.join(working_dir, 'corpus.' + target_lang)
fileutils.merge([corpus.get_file(target_lang) for corpus in reference_corpora], target_merged_corpus)
# Run MERT algorithm
with cmdlogger.step('Tuning') as _:
# Start MERT
decoder_flags = ['--port', str(self.api.port)]
if not context_enabled:
decoder_flags.append('--skip-context-analysis')
decoder_flags.append('1')
fileutils.makedirs(mert_wd, exist_ok=True)
with tempfile.NamedTemporaryFile() as runtime_moses_ini:
command = [self._mert_script, source_merged_corpus, target_merged_corpus,
self._mert_i_script, runtime_moses_ini.name, '--threads',
str(multiprocessing.cpu_count()), '--mertdir', cli.BIN_DIR,
'--mertargs', '\'--binary --sctype BLEU\'', '--working-dir', mert_wd, '--nbest', '100',
'--decoder-flags', '"' + ' '.join(decoder_flags) + '"', '--nonorm', '--closest',
'--no-filter-phrase-table']
if not random_seeds:
command.append('--predictable-seeds')
if max_iterations > 0:
command.append('--maximum-iterations={num}'.format(num=max_iterations))
with open(self.engine.get_logfile('mert'), 'wb') as log:
shell.execute(' '.join(command), stdout=log, stderr=log)
# Read optimized configuration
with cmdlogger.step('Applying changes') as _:
bleu_score = 0
weights = {}
found_weights = False
with open(os.path.join(mert_wd, 'moses.ini')) as moses_ini:
for line in moses_ini:
line = line.strip()
if len(line) == 0:
continue
elif found_weights:
tokens = line.split()
weights[tokens[0].rstrip('=')] = [float(val) for val in tokens[1:]]
elif line.startswith('# BLEU'):
bleu_score = float(line.split()[2])
elif line == '[weight]':
found_weights = True
_ = self.api.update_features(weights)
cmdlogger.completed(bleu_score)
finally:
if not debug:
self.engine.clear_tempdir()
