Source code for paddlenlp.transformers.rembert.tokenizer

# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at

#     http://www.apache.org/licenses/LICENSE-2.0

# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import os
from shutil import copyfile
from typing import List, Optional

import sentencepiece as spm

from .. import PretrainedTokenizer

__all__ = ["RemBertTokenizer"]

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"rembert": 512}


[docs]class RemBertTokenizer(PretrainedTokenizer): """ Construct a RemBertTokenizer. For more information regarding those methods, please refer to this superclass. Args: vocab_file (str): The vocabulary file path (ends with '.txt') required to instantiate a `WordpieceTokenizer`. do_lower_case (bool, optional): Whether or not to lowercase the input when tokenizing. Defaults to `False`. unk_token (str, optional): A special token representing the *unknown (out-of-vocabulary)* token. An unknown token is set to be `unk_token` inorder to be converted to an ID. Defaults to "[UNK]". sep_token (str, optional): A special token separating two different sentences in the same input. Defaults to "[SEP]". pad_token (str, optional): A special token used to make arrays of tokens the same size for batching purposes. Defaults to "[PAD]". cls_token (str, optional): A special token used for sequence classification. It is the last token of the sequence when built with special tokens. Defaults to "[CLS]". mask_token (str, optional): A special token representing a masked token. This is the token used in the masked language modeling task which the model tries to predict the original unmasked ones. Defaults to "[MASK]". Examples: .. code-block:: from paddlenlp.transformers import RemBertTokenizer tokenizer = RemBertTokenizer.from_pretrained('rembert') inputs = tokenizer('欢迎使用飞桨!') print(inputs) ''' {'input_ids': [312, 573, 36203, 3916, 9744, 242391, 646, 313], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0]} ''' """ resource_files_names = {"vocab_file": "sentencepiece.model"} pretrained_resource_files_map = { "vocab_file": { "rembert": "https://bj.bcebos.com/paddlenlp/models/transformers/rembert/sentencepiece.model", }, } pretrained_init_configuration = { "rembert": {"do_lower_case": False}, } max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES def __init__( self, vocab_file, do_lower_case=False, remove_space=True, keep_accents=True, cls_token="[CLS]", unk_token="[UNK]", sep_token="[SEP]", pad_token="[PAD]", mask_token="[MASK]", **kwargs ): self.do_lower_case = do_lower_case self.remove_space = remove_space self.keep_accents = keep_accents self.vocab_file = vocab_file self.sp_model = spm.SentencePieceProcessor() self.sp_model.Load(vocab_file) @property def vocab_size(self): return len(self.sp_model)
[docs] def get_vocab(self): vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)} vocab.update(self.added_tokens_encoder) return vocab
def __getstate__(self): state = self.__dict__.copy() state["sp_model"] = None return state def __setstate__(self, d): self.__dict__ = d self.sp_model = spm.SentencePieceProcessor() self.sp_model.Load(self.vocab_file) def _tokenize(self, text, sample=False): """Tokenize a string.""" pieces = self.sp_model.EncodeAsPieces(text) return pieces def _convert_token_to_id(self, token): """Converts a token (str) in an id using the vocab.""" return self.sp_model.PieceToId(token) def _convert_id_to_token(self, index): """Converts an index (integer) in a token (str) using the vocab.""" return self.sp_model.IdToPiece(index)
[docs] def convert_tokens_to_string(self, tokens): out_string = self.sp_model.decode_pieces(tokens) return out_string
[docs] def build_inputs_with_special_tokens( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None ) -> List[int]: """ Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A REMBERT sequence has the following format: - single sequence: ``[CLS] X [SEP]`` - pair of sequences: ``[CLS] A [SEP] B [SEP]`` Args: token_ids_0 (:obj:`List[int]`): List of IDs to which the special tokens will be added. token_ids_1 (:obj:`List[int]`, `optional`): Optional second list of IDs for sequence pairs. Returns: :obj:`List[int]`: List of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens. """ sep = [self.sep_token_id] cls = [self.cls_token_id] if token_ids_1 is None: return cls + token_ids_0 + sep return cls + token_ids_0 + sep + token_ids_1 + sep
[docs] def get_special_tokens_mask( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False ) -> List[int]: """ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer ``prepare_for_model`` method. Args: token_ids_0 (:obj:`List[int]`): List of IDs. token_ids_1 (:obj:`List[int]`, `optional`): Optional second list of IDs for sequence pairs. already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`): Whether or not the token list is already formatted with special tokens for the model. Returns: :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. """ if already_has_special_tokens: if token_ids_1 is not None: raise ValueError( "You should not supply a second sequence if the provided sequence of " "ids is already formatted with special tokens for the model." ) return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0)) if token_ids_1 is not None: return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1] return [1] + ([0] * len(token_ids_0)) + [1]
[docs] def create_token_type_ids_from_sequences( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None ) -> List[int]: """ Create a mask from the two sequences passed to be used in a sequence-pair classification task. A RemBERT sequence pair mask has the following format: :: 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 | first sequence | second sequence | If :obj:`token_ids_1` is :obj:`None`, this method only returns the first portion of the mask (0s). Args: token_ids_0 (:obj:`List[int]`): List of IDs. token_ids_1 (:obj:`List[int]`, `optional`): Optional second list of IDs for sequence pairs. Returns: :obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given sequence(s). """ sep = [self.sep_token_id] cls = [self.cls_token_id] if token_ids_1 is None: return len(cls + token_ids_0 + sep) * [0] return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
[docs] def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None): if not os.path.isdir(save_directory): raise ValueError("Vocabulary path ({}) should be a directory".format(save_directory)) return None out_vocab_file = os.path.join( save_directory, (filename_prefix + "-" if filename_prefix else "") + "sentencepiece.model" ) if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file): copyfile(self.vocab_file, out_vocab_file) return (out_vocab_file,)