File size: 8,777 Bytes
4c65bff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
# coding=utf-8
# Copyright The HuggingFace Inc. team. 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.
"""Tokenization classes for ConvBERT."""
import json
from typing import List, Optional, Tuple
from tokenizers import normalizers
from ...tokenization_utils_fast import PreTrainedTokenizerFast
from ...utils import logging
from .tokenization_convbert import ConvBertTokenizer
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"YituTech/conv-bert-base": "https://huggingface.co/YituTech/conv-bert-base/resolve/main/vocab.txt",
"YituTech/conv-bert-medium-small": (
"https://huggingface.co/YituTech/conv-bert-medium-small/resolve/main/vocab.txt"
),
"YituTech/conv-bert-small": "https://huggingface.co/YituTech/conv-bert-small/resolve/main/vocab.txt",
}
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"YituTech/conv-bert-base": 512,
"YituTech/conv-bert-medium-small": 512,
"YituTech/conv-bert-small": 512,
}
PRETRAINED_INIT_CONFIGURATION = {
"YituTech/conv-bert-base": {"do_lower_case": True},
"YituTech/conv-bert-medium-small": {"do_lower_case": True},
"YituTech/conv-bert-small": {"do_lower_case": True},
}
# Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with bert-base-cased->YituTech/conv-bert-base, Bert->ConvBert, BERT->ConvBERT
class ConvBertTokenizerFast(PreTrainedTokenizerFast):
r"""
Construct a "fast" ConvBERT tokenizer (backed by HuggingFace's *tokenizers* library). Based on WordPiece.
This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
Args:
vocab_file (`str`):
File containing the vocabulary.
do_lower_case (`bool`, *optional*, defaults to `True`):
Whether or not to lowercase the input when tokenizing.
unk_token (`str`, *optional*, defaults to `"[UNK]"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
sep_token (`str`, *optional*, defaults to `"[SEP]"`):
The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
sequence classification or for a text and a question for question answering. It is also used as the last
token of a sequence built with special tokens.
pad_token (`str`, *optional*, defaults to `"[PAD]"`):
The token used for padding, for example when batching sequences of different lengths.
cls_token (`str`, *optional*, defaults to `"[CLS]"`):
The classifier token which is used when doing sequence classification (classification of the whole sequence
instead of per-token classification). It is the first token of the sequence when built with special tokens.
mask_token (`str`, *optional*, defaults to `"[MASK]"`):
The token used for masking values. This is the token used when training this model with masked language
modeling. This is the token which the model will try to predict.
clean_text (`bool`, *optional*, defaults to `True`):
Whether or not to clean the text before tokenization by removing any control characters and replacing all
whitespaces by the classic one.
tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see [this
issue](https://github.com/huggingface/transformers/issues/328)).
strip_accents (`bool`, *optional*):
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
value for `lowercase` (as in the original ConvBERT).
wordpieces_prefix (`str`, *optional*, defaults to `"##"`):
The prefix for subwords.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
slow_tokenizer_class = ConvBertTokenizer
def __init__(
self,
vocab_file=None,
tokenizer_file=None,
do_lower_case=True,
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
mask_token="[MASK]",
tokenize_chinese_chars=True,
strip_accents=None,
**kwargs,
):
super().__init__(
vocab_file,
tokenizer_file=tokenizer_file,
do_lower_case=do_lower_case,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
**kwargs,
)
normalizer_state = json.loads(self.backend_tokenizer.normalizer.__getstate__())
if (
normalizer_state.get("lowercase", do_lower_case) != do_lower_case
or normalizer_state.get("strip_accents", strip_accents) != strip_accents
or normalizer_state.get("handle_chinese_chars", tokenize_chinese_chars) != tokenize_chinese_chars
):
normalizer_class = getattr(normalizers, normalizer_state.pop("type"))
normalizer_state["lowercase"] = do_lower_case
normalizer_state["strip_accents"] = strip_accents
normalizer_state["handle_chinese_chars"] = tokenize_chinese_chars
self.backend_tokenizer.normalizer = normalizer_class(**normalizer_state)
self.do_lower_case = do_lower_case
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
"""
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. A ConvBERT sequence has the following format:
- single sequence: `[CLS] X [SEP]`
- pair of sequences: `[CLS] A [SEP] B [SEP]`
Args:
token_ids_0 (`List[int]`):
List of IDs to which the special tokens will be added.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
"""
output = [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
if token_ids_1 is not None:
output += token_ids_1 + [self.sep_token_id]
return output
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 ConvBERT
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 `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [token type IDs](../glossary#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]
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
files = self._tokenizer.model.save(save_directory, name=filename_prefix)
return tuple(files)
|