def __init__(self, pipeline, language):
self.tagger = pipeline.turbo_interface.create_tagger()
self.parser = pipeline.turbo_interface.create_parser()
self.lemmatizer = None
if language == 'PT':
self.sent_tokenizer = nltk.data.load(
'tokenizers/punkt/portuguese.pickle')
self.word_tokenizer = tokenizer_PT.PortugueseFlorestaWordTokenizer(
)
self.tagger.load_tagger_model(
'/home/atm/workspace/CPP/TurboParser/models/portuguese_floresta_v2.0_nomwe_auto/portuguese_floresta_v2.0_nomwe_auto_tagger.model'
)
self.parser.load_parser_model(
'/home/atm/workspace/CPP/TurboParser/models/portuguese_floresta_v2.0_nomwe_auto/portuguese_floresta_v2.0_nomwe_auto_parser_pruned-true_model-standard.model'
)
self.lemmatizer = lemmatizer.BasicLemmatizer()
self.lemmatizer.load_lemmatizer_model(
'/home/atm/workspace/CPP/TurboParser/models/portuguese_floresta_v2.0_nomwe_auto/portuguese_floresta_v2.0_nomwe_auto_lemmatizer.model'
)
elif language == 'PT-Cintil':
self.sent_tokenizer = nltk.data.load(
'tokenizers/punkt/portuguese.pickle')
self.word_tokenizer = tokenizer_PT.PortugueseCintilWordTokenizer()
self.tagger.load_tagger_model(
'/home/atm/workspace/CPP/TurboParser/models/portuguese_cetem-depbank/portuguese_cetem-depbank_tagger.model'
)
self.parser.load_parser_model(
'/home/atm/workspace/CPP/TurboParser/models/portuguese_cetem-depbank/portuguese_cetem-depbank_parser_pruned-true_model-standard.model'
)
elif language == 'ES':
self.sent_tokenizer = nltk.data.load(
'tokenizers/punkt/spanish.pickle')
self.word_tokenizer = nltk.TreebankWordTokenizer() # For now...
self.tagger.load_tagger_model(
'/home/atm/workspace/CPP/TurboParser/models/spanish_conll2009_v2.0_nomwe_auto/spanish_conll2009_v2.0_nomwe_auto_tagger.model'
)
self.parser.load_parser_model(
'/home/atm/workspace/CPP/TurboParser/models/spanish_conll2009_v2.0_nomwe_auto/spanish_conll2009_v2.0_nomwe_auto_parser_pruned-true_model-standard.model'
)
self.lemmatizer = lemmatizer.BasicLemmatizer()
self.lemmatizer.load_lemmatizer_model(
'/home/atm/workspace/CPP/TurboParser/models/spanish_conll2009_v2.0_nomwe_auto/spanish_conll2009_v2.0_nomwe_auto_lemmatizer.model'
)
elif language == 'EN':
self.sent_tokenizer = nltk.data.load(
'tokenizers/punkt/english.pickle')
self.word_tokenizer = nltk.TreebankWordTokenizer()
self.tagger.load_tagger_model(
'/home/atm/workspace/CPP/TurboParser/models/english_proj/english_proj_tagger.model'
)
self.parser.load_parser_model(
'/home/atm/workspace/CPP/TurboParser/models/english_proj/english_proj_parser_pruned-true_model-standard.model'
)
else:
raise NotImplementedError
def __init__(self, pipeline, language):
self.tagger = None
self.parser = None
self.semantic_parser = None
self.lemmatizer = None
if language not in pipeline.models:
print 'Error: no model for language %s.' % language
raise NotImplementedError
if 'splitter' in pipeline.models[language]:
self.sent_tokenizer = nltk.data.load(pipeline.models[language]['splitter'])
else:
# If no splitter is specified, use the English model.
self.sent_tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
if language == 'PT':
self.word_tokenizer = tokenizer_PT.PortugueseFlorestaWordTokenizer()
elif language == 'PT-Cintil':
self.word_tokenizer = tokenizer_PT.PortugueseCintilWordTokenizer()
else:
self.word_tokenizer = nltk.TreebankWordTokenizer() # For now...
if 'tagger' in pipeline.models[language]:
self.tagger = pipeline.turbo_interface.create_tagger()
self.tagger.load_tagger_model(pipeline.models[language]['tagger'])
if 'parser' in pipeline.models[language]:
self.parser = pipeline.turbo_interface.create_parser()
self.parser.load_parser_model(pipeline.models[language]['parser'])
if 'lemmatizer' in pipeline.models[language]:
self.lemmatizer = lemmatizer.BasicLemmatizer()
self.lemmatizer.load_lemmatizer_model(pipeline.models[language]['lemmatizer'])
if 'semantic_parser' in pipeline.models[language]:
self.semantic_parser = pipeline.turbo_interface.create_semantic_parser()
self.semantic_parser.load_semantic_parser_model(pipeline.models[language]['semantic_parser'])
def __init__(self, pipeline, language):
self.tagger = None
self.morphological_tagger = None
self.entity_recognizer = None
self.parser = None
self.semantic_parser = None
self.lemmatizer = None
self.coreference_resolver = None
if language not in pipeline.models:
print('Error: no model for language %s.' % language)
raise NotImplementedError
if 'splitter' in pipeline.models[language]:
self.sent_tokenizer = nltk.data.load(
pipeline.models[language]['splitter'])
else:
# If no splitter is specified, use the English model.
self.sent_tokenizer = nltk.data.load(
'tokenizers/punkt/english.pickle')
if 'tokenizer' in pipeline.models[language]:
tokenizer_language = pipeline.models[language]['tokenizer']
self.word_tokenizer = \
UniversalWordTokenizer(language=tokenizer_language)
else:
self.word_tokenizer = UniversalWordTokenizer(language='none')
if 'tagger' in pipeline.models[language]:
self.tagger = pipeline.turbo_interface.create_tagger()
self.tagger.load_tagger_model(pipeline.models[language]['tagger'])
if 'morphological_tagger' in pipeline.models[language]:
self.morphological_tagger = pipeline.turbo_interface.create_morphological_tagger(
)
self.morphological_tagger.load_morphological_tagger_model(
pipeline.models[language]['morphological_tagger'])
if 'entity_recognizer' in pipeline.models[language]:
self.entity_recognizer = pipeline.turbo_interface.create_entity_recognizer(
)
self.entity_recognizer.load_entity_recognizer_model(
pipeline.models[language]['entity_recognizer'])
if 'parser' in pipeline.models[language]:
self.parser = pipeline.turbo_interface.create_parser()
self.parser.load_parser_model(pipeline.models[language]['parser'])
if 'lemmatizer' in pipeline.models[language]:
self.lemmatizer = lemmatizer.BasicLemmatizer()
self.lemmatizer.load_lemmatizer_model(
pipeline.models[language]['lemmatizer'])
if 'semantic_parser' in pipeline.models[language]:
self.semantic_parser = pipeline.turbo_interface.create_semantic_parser(
)
self.semantic_parser.load_semantic_parser_model(
pipeline.models[language]['semantic_parser'])
if 'coreference_resolver' in pipeline.models[language]:
self.coreference_resolver = pipeline.turbo_interface.create_coreference_resolver(
)
self.coreference_resolver.load_coreference_resolver_model(
pipeline.models[language]['coreference_resolver'])