本文整理汇总了Python中allennlp.data.tokenizers.Tokenizer方法的典型用法代码示例。如果您正苦于以下问题:Python tokenizers.Tokenizer方法的具体用法?Python tokenizers.Tokenizer怎么用?Python tokenizers.Tokenizer使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类allennlp.data.tokenizers
的用法示例。
在下文中一共展示了tokenizers.Tokenizer方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(
self,
token_indexers: Dict[str, TokenIndexer] = None,
tokenizer: Tokenizer = None,
segment_sentences: bool = False,
max_sequence_length: int = None,
skip_label_indexing: bool = False,
**kwargs,
) -> None:
super().__init__(**kwargs)
self._tokenizer = tokenizer or SpacyTokenizer()
self._segment_sentences = segment_sentences
self._max_sequence_length = max_sequence_length
self._skip_label_indexing = skip_label_indexing
self._token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer()}
if self._segment_sentences:
self._sentence_segmenter = SpacySentenceSplitter()
示例2: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(
self,
target_namespace: str,
source_tokenizer: Tokenizer = None,
target_tokenizer: Tokenizer = None,
source_token_indexers: Dict[str, TokenIndexer] = None,
target_token_indexers: Dict[str, TokenIndexer] = None,
lazy: bool = False,
) -> None:
super().__init__(lazy)
self._target_namespace = target_namespace
self._source_tokenizer = source_tokenizer or SpacyTokenizer()
self._target_tokenizer = target_tokenizer or self._source_tokenizer
self._source_token_indexers = source_token_indexers or {
"tokens": SingleIdTokenIndexer()
}
self._target_token_indexers = (
target_token_indexers or self._source_token_indexers
)
warnings.warn(
"The 'copynet' dataset reader has been deprecated in favor of the "
"'copynet_seq2seq' dataset reader (now part of the AllenNLP library).",
DeprecationWarning,
)
示例3: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(
self,
target_namespace: str,
source_tokenizer: Tokenizer = None,
target_tokenizer: Tokenizer = None,
source_token_indexers: Dict[str, TokenIndexer] = None,
target_token_indexers: Dict[str, TokenIndexer] = None,
lazy: bool = False,
) -> None:
source_tokenizer = source_tokenizer or NL2BashWordSplitter()
target_tokenizer = target_tokenizer or source_tokenizer
super().__init__(
target_namespace,
source_tokenizer=source_tokenizer,
target_tokenizer=target_tokenizer,
source_token_indexers=source_token_indexers,
target_token_indexers=target_token_indexers,
lazy=lazy,
)
示例4: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
debug: bool = False,
tokenizer: Tokenizer = None,
include_more_numbers: bool = False,
skip_when_all_empty: List[str] = None,
max_number_of_answer: int = 8,
max_number_count: int = 10,
logger = None) -> None:
super().__init__()
self.debug = debug
self._tokenizer = tokenizer or WordTokenizer()
self.include_more_numbers = include_more_numbers
self.max_number_of_answer = max_number_of_answer
self.max_number_count = max_number_count
self.skip_when_all_empty = skip_when_all_empty if skip_when_all_empty is not None else []
for item in self.skip_when_all_empty:
assert item in ["passage_span", "question_span", "addition_subtraction", "counting", "negation"], \
f"Unsupported skip type: {item}"
self.logger = logger
示例5: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self, utterances: List[str], tokenizer: Tokenizer = None) -> None:
if AtisWorld.sql_table_context is None:
AtisWorld.sql_table_context = AtisSqlTableContext(
atis_tables.ALL_TABLES, atis_tables.TABLES_WITH_STRINGS, AtisWorld.database_file
)
self.utterances: List[str] = utterances
self.tokenizer = tokenizer if tokenizer else SpacyTokenizer()
self.tokenized_utterances = [
self.tokenizer.tokenize(utterance) for utterance in self.utterances
]
self.dates = self._get_dates()
self.linked_entities = self._get_linked_entities()
entities, linking_scores = self._flatten_entities()
# This has shape (num_entities, num_utterance_tokens).
self.linking_scores: numpy.ndarray = linking_scores
self.entities: List[str] = entities
self.grammar: Grammar = self._update_grammar()
self.valid_actions = initialize_valid_actions(self.grammar, KEYWORDS)
示例6: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(
self,
lazy: bool = False,
tokenizer: Tokenizer = None,
sentence_token_indexers: Dict[str, TokenIndexer] = None,
nonterminal_indexers: Dict[str, TokenIndexer] = None,
terminal_indexers: Dict[str, TokenIndexer] = None,
output_agendas: bool = True,
) -> None:
super().__init__(lazy)
self._tokenizer = tokenizer or SpacyTokenizer()
self._sentence_token_indexers = sentence_token_indexers or {
"tokens": SingleIdTokenIndexer()
}
self._nonterminal_indexers = nonterminal_indexers or {
"tokens": SingleIdTokenIndexer("rule_labels")
}
self._terminal_indexers = terminal_indexers or {
"tokens": SingleIdTokenIndexer("rule_labels")
}
self._output_agendas = output_agendas
示例7: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
lazy: bool = False,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
words_per_instance: int = 35
) -> None:
super().__init__(lazy)
self._tokenizer = tokenizer or WordTokenizer(
start_tokens=[START_SYMBOL],
end_tokens=[END_SYMBOL]
)
self._token_indexers = token_indexers or {
"tokens": SingleIdTokenIndexer(namespace="tokens", lowercase_tokens=True)
}
self._words_per_instance = words_per_instance
示例8: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
lazy: bool = False,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
clean_citation: bool = True,
with_elmo: bool = False
) -> None:
super().__init__(lazy)
self._clean_citation = clean_citation
self._tokenizer = tokenizer or WordTokenizer()
self._token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer()}
if with_elmo:
self._token_indexers = {"elmo": ELMoTokenCharactersIndexer(),
"tokens": SingleIdTokenIndexer()}
else:
self._token_indexers = {"tokens": SingleIdTokenIndexer()}
示例9: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
source_add_start_token: bool = True,
max_doc_length:int = -1,
max_query_length:int = -1,
min_doc_length:int = -1,
min_query_length:int = -1,
lazy: bool = False) -> None:
super().__init__(lazy)
self._tokenizer = tokenizer or WordTokenizer() # little bit faster, useful for multicore proc. word_splitter=SimpleWordSplitter()
self._token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer(lowercase_tokens=True)}
self._source_add_start_token = source_add_start_token
self.max_doc_length = max_doc_length
self.max_query_length = max_query_length
self.min_doc_length = min_doc_length
self.min_query_length = min_query_length
self.padding_value = Token(text = "@@PADDING@@",text_id=0)
示例10: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
source_add_start_token: bool = True,
max_doc_length:int = -1,
max_query_length:int = -1,
min_doc_length:int = -1,
min_query_length:int = -1,
lazy: bool = False) -> None:
super().__init__(lazy)
self._tokenizer = tokenizer
self._token_indexers = token_indexers
self._source_add_start_token = source_add_start_token
self.max_doc_length = max_doc_length
self.max_query_length = max_query_length
self.min_doc_length = min_doc_length
self.min_query_length = min_query_length
self.padding_value = Token(text = "[PAD]",text_id=0)
self.sep_value = Token(text = "[SEP]")
开发者ID:sebastian-hofstaetter,项目名称:transformer-kernel-ranking,代码行数:22,代码来源:bert_labeled_tuple_loader.py
示例11: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
tokenizer: Tokenizer,
language: str,
source_token_indexers: Dict[str, TokenIndexer] = None,
max_sentences_count: int = 100,
sentence_max_tokens: int = 100,
lowercase: bool = True,
lazy: bool = True) -> None:
super().__init__(lazy=lazy)
self._tokenizer = tokenizer
self._lowercase = lowercase
self._language = language
self._max_sentences_count = max_sentences_count
self._sentence_max_tokens = sentence_max_tokens
self._source_token_indexers = source_token_indexers or {"tokens": SingleIdTokenIndexer()}
示例12: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
token_indexers: Dict[str, TokenIndexer] = None,
tokenizer: Tokenizer = None,
max_sequence_length: int = None,
ignore_labels: bool = False,
sample: int = None,
skip_label_indexing: bool = False,
lazy: bool = False) -> None:
super().__init__(lazy=lazy,
token_indexers=token_indexers,
tokenizer=tokenizer,
max_sequence_length=max_sequence_length,
skip_label_indexing=skip_label_indexing)
self._tokenizer = tokenizer or WordTokenizer()
self._sample = sample
self._max_sequence_length = max_sequence_length
self._ignore_labels = ignore_labels
self._skip_label_indexing = skip_label_indexing
self._token_indexers = token_indexers or {'tokens': SingleIdTokenIndexer()}
if self._segment_sentences:
self._sentence_segmenter = SpacySentenceSplitter()
示例13: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
lazy: bool = False,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
) -> None:
super().__init__(lazy)
self._tokenizer = tokenizer or WordTokenizer()
self._token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer()}
示例14: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
source_add_start_token: bool = True,
max_doc_length:int = -1,
max_query_length:int = -1,
lazy: bool = False) -> None:
super().__init__(lazy)
self._tokenizer = tokenizer or WordTokenizer() # little bit faster, useful for multicore proc. word_splitter=SimpleWordSplitter()
self._token_indexers = token_indexers or {"tokens": SingleIdTokenIndexer(lowercase_tokens=True)}
self._source_add_start_token = source_add_start_token
self.max_doc_length = max_doc_length
self.max_query_length = max_query_length
示例15: __init__
# 需要导入模块: from allennlp.data import tokenizers [as 别名]
# 或者: from allennlp.data.tokenizers import Tokenizer [as 别名]
def __init__(self,
lazy: bool = False,
tokenizer: Tokenizer = None,
token_indexers: Dict[str, TokenIndexer] = None,
max_token_len: int = 512):
super().__init__(lazy)
self._tokenizer = tokenizer or CharacterTokenizer()
self._token_indexers = token_indexers or {'tokens': SingleIdTokenIndexer()}
self._max_token_len = max_token_len