Whitespace Tokenizer
import collections
import os
import pdb
import logging
import numpy as np
from typing import List, Optional, Tuple
from transformers import PreTrainedTokenizer
logger = logging.getLogger(__name__)
load_vocab
Loads a vocabulary file into a dictionary.
def load_vocab(vocab_file, return_embeddings=False):
"""Loads a vocabulary file into a dictionary."""
vocab = collections.OrderedDict()
vocab["[PAD]"] = 0
with open(vocab_file, "r", encoding="utf-8") as reader:
lines = reader.readlines()
num_embeddings = len(lines) + 1
embedding_dim = len(lines[0].split()) - 1
for index, line in enumerate(lines):
token = " ".join(line.split()[:-embedding_dim])
if token in vocab:
token = f"{token}_{index+1}"
vocab[token] = index + 1
if return_embeddings:
word_embeddings = np.zeros((num_embeddings, embedding_dim), dtype=np.float32)
for index, line in enumerate(lines):
embedding = [float(value) for value in line.strip().split()[-embedding_dim:]]
word_embeddings[index+1] = embedding
return word_embeddings
return vocab
whitespace_tokenize
Runs basic whitespace cleaning and splitting on a piece of text.
def whitespace_tokenize(text):
"""Runs basic whitespace cleaning and splitting on a piece of text."""
text = text.strip()
if not text:
return []
tokens = text.split()
return tokens
VOCAB_FILES_NAMES = {"vocab_file": "vec.txt"}
PRETRAINED_VOCAB_FILES_MAP = {}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}
PRETRAINED_INIT_CONFIGURATION = {}
WordLevelTokenizer
Construct a BERT tokenizer. Based on WordPiece.
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.
class WordLevelTokenizer(PreTrainedTokenizer):
r"""
Construct a BERT tokenizer. Based on WordPiece.
This tokenizer inherits from [`PreTrainedTokenizer`] 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.
do_basic_tokenize (`bool`, *optional*, defaults to `True`):
Whether or not to do basic tokenization before WordPiece.
never_split (`Iterable`, *optional*):
Collection of tokens which will never be split during tokenization. Only has an effect when
`do_basic_tokenize=True`
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.
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 BERT).
"""
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
def __init__(
self,
vocab_file,
do_lower_case=True,
never_split=None,
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
strip_accents=None,
model_max_length=512,
**kwargs
):
kwargs["model_max_length"] = model_max_length
super().__init__(
do_lower_case=do_lower_case,
never_split=never_split,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
strip_accents=strip_accents,
**kwargs,
)
if not os.path.isfile(vocab_file):
raise ValueError(
f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained"
" model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
)
self.vocab = load_vocab(vocab_file)
# insert special token
for token in [unk_token, sep_token, pad_token, cls_token]:
if token not in self.vocab:
self.vocab[token] = len(self.vocab)
self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
self.whitespace_tokenizer = WhitespaceTokenizer(vocab=self.vocab, do_lower_case=do_lower_case, unk_token=self.unk_token)
@property
def do_lower_case(self):
return self.whitespace_tokenizer.do_lower_case
@property
def vocab_size(self):
return len(self.vocab)
def get_vocab(self):
return dict(self.vocab, **self.added_tokens_encoder)
def _tokenize(self, text):
if self.do_lower_case:
text = text.lower()
split_tokens = self.whitespace_tokenizer.tokenize(text)
return split_tokens
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.vocab.get(token, self.vocab.get(self.unk_token))
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.ids_to_tokens.get(index, self.unk_token)
def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (string) in a single string."""
out_string = " ".join(tokens).replace(" ##", "").strip()
return out_string
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 BERT 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.
"""
if token_ids_1 is None:
return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
cls = [self.cls_token_id]
sep = [self.sep_token_id]
return cls + token_ids_0 + sep + token_ids_1 + sep
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 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
`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:
return super().get_special_tokens_mask(
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
)
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]
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 BERT 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]:
index = 0
if os.path.isdir(save_directory):
vocab_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
)
else:
vocab_file = (filename_prefix + "-" if filename_prefix else "") + save_directory
with open(vocab_file, "w", encoding="utf-8") as writer:
for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
if index != token_index:
logger.warning(
f"Saving vocabulary to {vocab_file}: vocabulary indices are not consecutive."
" Please check that the vocabulary is not corrupted!"
)
index = token_index
writer.write(token + "\n")
index += 1
return (vocab_file,)
WhitespaceTokenizer
Runs WordPiece tokenization.
class WhitespaceTokenizer(object):
"""Runs WordPiece tokenization."""
def __init__(self, vocab, do_lower_case, unk_token):
self.vocab = vocab
self.do_lower_case = do_lower_case
self.unk_token = unk_token
def tokenize(self, text):
"""
Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
tokenization using the given vocabulary.
For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.
Args:
text: A single token or whitespace separated tokens. This should have
already been passed through *BasicTokenizer*.
Returns:
A list of wordpiece tokens.
"""
output_tokens = []
for token in whitespace_tokenize(text):
if token in self.vocab:
output_tokens.append(token)
else:
output_tokens.append(self.unk_token)
return output_tokens