def train(self, corpora, lang, working_dir=".", log_file=None):
LanguageModel.train(self, corpora, lang, working_dir, log_file)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, "w")
# Collapse all corpora into a single text file
merged_corpus = os.path.join(working_dir, "merge")
fileutils.merge([corpus.get_file(lang) for corpus in corpora], merged_corpus)
input_se = os.path.join(working_dir, "static_input.se")
temp = os.path.join(working_dir, "temp")
arpa_file = os.path.join(working_dir, "static_lm.arpa")
# Add start and end symbols
with open(merged_corpus) as stdin:
with open(input_se, "w") as stdout:
shell.execute([self._addbound_bin], stdin=stdin, stdout=stdout, stderr=log)
# Creating lm in ARPA format
command = [
self._buildlm_bin,
"-i",
input_se,
"-k",
str(cpu_count()),
"-o",
arpa_file,
"-n",
str(self._order),
"-s",
"witten-bell",
"-t",
temp,
"-l",
"/dev/stdout",
"-irstlm",
self._irstlm_dir,
"--PruneSingletons",
]
shell.execute(command, stderr=log)
# Create binary lm
command = [self._compilelm_bin, arpa_file + ".gz", self._model]
shell.execute(command, stderr=log)
finally:
if log_file is not None:
log.close()
def train(self, corpora, lang, working_dir='.', log_file=None):
LanguageModel.train(self, corpora, lang, working_dir, log_file)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'w')
# Collapse all corpora into a single text file
merged_corpus = os.path.join(working_dir, 'merge')
fileutils.merge([corpus.get_file(lang) for corpus in corpora],
merged_corpus)
input_se = os.path.join(working_dir, 'static_input.se')
temp = os.path.join(working_dir, 'temp')
arpa_file = os.path.join(working_dir, 'static_lm.arpa')
# Add start and end symbols
with open(merged_corpus) as stdin:
with open(input_se, 'w') as stdout:
shell.execute([self._addbound_bin],
stdin=stdin,
stdout=stdout,
stderr=log)
# Creating lm in ARPA format
command = [
self._buildlm_bin, '-i', input_se, '-k',
str(cpu_count()), '-o', arpa_file, '-n',
str(self._order), '-s', 'witten-bell', '-t', temp, '-l',
'/dev/stdout', '-irstlm', self._irstlm_dir, '--PruneSingletons'
]
shell.execute(command, stderr=log)
# Create binary lm
command = [self._compilelm_bin, arpa_file + '.gz', self._model]
shell.execute(command, stderr=log)
finally:
if log_file is not None:
log.close()
def train(self, corpora, lang, working_dir=".", log_file=None):
LanguageModel.train(self, corpora, lang, working_dir, log_file)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, "w") if isinstance(log_file, str) else log_file
# Collapse all corpora into a single text file
merged_corpus = os.path.join(working_dir, "merge")
fileutils.merge([corpus.get_file(lang) for corpus in corpora], merged_corpus)
# Create language model in ARPA format
arpa_file = os.path.join(working_dir, "lm.arpa")
arpa_command = [
self._lmplz_bin,
"--discount_fallback",
"-o",
str(self._order),
"-S",
str(self.get_mem_percent()) + "%",
"-T",
working_dir,
]
if self._order > 2 and self.prune:
arpa_command += ["--prune", "0", "0", "1"]
with open(merged_corpus) as stdin:
with open(arpa_file, "w") as stdout:
shell.execute(arpa_command, stdin=stdin, stdout=stdout, stderr=log)
# Binarize ARPA file
binarize_command = [self._bbinary_bin, arpa_file, self._model]
shell.execute(binarize_command, stdout=log, stderr=log)
finally:
if log_file is not None and isinstance(log_file, str):
log.close()
def train(self, corpora, lang, working_dir='.', log_file=None):
LanguageModel.train(self, corpora, lang, working_dir, log_file)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'w') if isinstance(log_file,
str) else log_file
# Collapse all corpora into a single text file
merged_corpus = os.path.join(working_dir, 'merge')
fileutils.merge([corpus.get_file(lang) for corpus in corpora],
merged_corpus)
# Create language model in ARPA format
arpa_file = os.path.join(working_dir, 'lm.arpa')
arpa_command = [
self._lmplz_bin, '--discount_fallback', '-o',
str(self._order), '-S',
str(self.get_mem_percent()) + '%', '-T', working_dir
]
if self._order > 2 and self.prune:
arpa_command += ['--prune', '0', '0', '1']
with open(merged_corpus) as stdin:
with open(arpa_file, 'w') as stdout:
shell.execute(arpa_command,
stdin=stdin,
stdout=stdout,
stderr=log)
# Binarize ARPA file
binarize_command = [self._bbinary_bin, arpa_file, self._model]
shell.execute(binarize_command, stdout=log, stderr=log)
finally:
if log_file is not None and isinstance(log_file, str):
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 = ParallelCorpus(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, tokenize=True, debug=False, context_enabled=True):
if corpora is None:
corpora = ParallelCorpus.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')
target_lang = self.engine.target_lang
source_lang = self.engine.source_lang
cmdlogger = _tuning_logger(4 if tokenize else 3)
cmdlogger.start(self, corpora)
working_dir = self.engine.get_tempdir('tuning')
mert_wd = os.path.join(working_dir, 'mert')
try:
original_corpora = corpora
# Tokenization
tokenized_corpora = original_corpora
if tokenize:
tokenizer_output = os.path.join(working_dir, 'tokenized_corpora')
fileutils.makedirs(tokenizer_output, exist_ok=True)
with cmdlogger.step('Corpus tokenization') as _:
tokenized_corpora = self.engine.preprocessor.process(corpora, tokenizer_output, print_tags=False,
print_placeholders=True,
original_spacing=False)
# Create merged corpus
with cmdlogger.step('Merging corpus') as _:
source_merged_corpus = os.path.join(working_dir, 'corpus.' + source_lang)
with open(source_merged_corpus, 'wb') as out:
original_root = original_corpora[0].root
for corpus in tokenized_corpora:
tokenized = corpus.get_file(source_lang)
original = os.path.join(original_root, corpus.name + '.' + source_lang)
out.write(tokenized + ':' + original + '\n')
target_merged_corpus = os.path.join(working_dir, 'corpus.' + target_lang)
fileutils.merge([corpus.get_file(target_lang) for corpus in tokenized_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', os.path.join(Moses.bin_path, 'bin'),
'--mertargs', '\'--binary --sctype BLEU\'', '--working-dir', mert_wd, '--nbest', '100',
'--decoder-flags', '"' + ' '.join(decoder_flags) + '"', '--nonorm', '--closest',
'--no-filter-phrase-table']
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()
def tune(self,
corpora=None,
tokenize=True,
debug=False,
context_enabled=True):
if corpora is None:
corpora = ParallelCorpus.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')
target_lang = self.engine.target_lang
source_lang = self.engine.source_lang
cmdlogger = _tuning_logger(4 if tokenize else 3)
cmdlogger.start(self, corpora)
working_dir = self.engine.get_tempdir('tuning')
mert_wd = os.path.join(working_dir, 'mert')
try:
original_corpora = corpora
# Tokenization
tokenized_corpora = original_corpora
if tokenize:
tokenizer_output = os.path.join(working_dir,
'tokenized_corpora')
fileutils.makedirs(tokenizer_output, exist_ok=True)
with cmdlogger.step('Corpus tokenization') as _:
tokenized_corpora = self.engine.preprocessor.process(
corpora,
tokenizer_output,
print_tags=False,
print_placeholders=True,
original_spacing=False)
# Create merged corpus
with cmdlogger.step('Merging corpus') as _:
source_merged_corpus = os.path.join(working_dir,
'corpus.' + source_lang)
with open(source_merged_corpus, 'wb') as out:
original_root = original_corpora[0].root
for corpus in tokenized_corpora:
tokenized = corpus.get_file(source_lang)
original = os.path.join(
original_root, corpus.name + '.' + source_lang)
out.write(tokenized + ':' + original + '\n')
target_merged_corpus = os.path.join(working_dir,
'corpus.' + target_lang)
fileutils.merge([
corpus.get_file(target_lang)
for corpus in tokenized_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',
os.path.join(Moses.bin_path, 'bin'), '--mertargs',
'\'--binary --sctype BLEU\'', '--working-dir', mert_wd,
'--nbest', '100', '--decoder-flags',
'"' + ' '.join(decoder_flags) + '"', '--nonorm',
'--closest', '--no-filter-phrase-table'
]
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()
def evaluate(self, corpora, heval_output=None, debug=False):
if len(corpora) == 0:
raise IllegalArgumentException('empty corpora')
if heval_output is not None:
fileutils.makedirs(heval_output, exist_ok=True)
target_lang = self._engine.target_lang
source_lang = self._engine.source_lang
logger = _evaluate_logger()
logger.start(corpora)
working_dir = self._engine.get_tempdir('evaluation')
try:
results = []
# Process references
with logger.step('Preparing corpora') as _:
corpora_path = os.path.join(working_dir, 'corpora')
corpora = self._xmlencoder.encode(corpora, corpora_path)
reference = os.path.join(working_dir, 'reference.' + target_lang)
source = os.path.join(working_dir, 'source.' + source_lang)
fileutils.merge([corpus.get_file(target_lang) for corpus in corpora], reference)
fileutils.merge([corpus.get_file(source_lang) for corpus in corpora], source)
if heval_output is not None:
self._heval_outputter.write(lang=target_lang, input_file=reference,
output_file=os.path.join(heval_output, 'reference.' + target_lang))
self._heval_outputter.write(lang=source_lang, input_file=source,
output_file=os.path.join(heval_output, 'source.' + source_lang))
# Translate
for translator in self._translators:
name = translator.name()
with logger.step('Translating with %s' % name) as _:
result = _EvaluationResult(translator)
results.append(result)
translations_path = os.path.join(working_dir, 'translations', result.id + '.raw')
xmltranslations_path = os.path.join(working_dir, 'translations', result.id)
fileutils.makedirs(translations_path, exist_ok=True)
try:
translated, mtt, parallelism = translator.translate(corpora, translations_path)
filename = result.id + '.' + target_lang
result.mtt = mtt
result.parallelism = parallelism
result.translated_corpora = self._xmlencoder.encode(translated, xmltranslations_path)
result.merge = os.path.join(working_dir, filename)
fileutils.merge([corpus.get_file(target_lang)
for corpus in result.translated_corpora], result.merge)
if heval_output is not None:
self._heval_outputter.write(lang=target_lang, input_file=result.merge,
output_file=os.path.join(heval_output, filename))
except TranslateError as e:
result.error = e
except Exception as e:
result.error = TranslateError('Unexpected ERROR: ' + str(e.message))
# Scoring
scorers = [(MatecatScore(), 'pes'), (BLEUScore(), 'bleu')]
for scorer, field in scorers:
with logger.step('Calculating %s' % scorer.name()) as _:
for result in results:
if result.error is not None:
continue
setattr(result, field, scorer.calculate(result.merge, reference))
logger.completed(results, scorers)
finally:
if not debug:
self._engine.clear_tempdir('evaluation')