fastNLP/fastNLP/transformers/torch/models/roberta/tokenization_roberta.py

# coding=utf-8
# Copyright 2018 The Open AI Team Authors and The HuggingFace Inc. team.
#
# 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 RoBERTa."""

from typing import List, Optional

from fastNLP.transformers.torch.tokenization_utils import AddedToken
from ..gpt2.tokenization_gpt2 import GPT2Tokenizer
from fastNLP.core.log import logger

__all__ = [
    "RobertaTokenizer",
]

VOCAB_FILES_NAMES = {
    "vocab_file": "vocab.json",
    "merges_file": "merges.txt",
}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "roberta-base": "https://huggingface.co/roberta-base/resolve/main/vocab.json",
        "roberta-large": "https://huggingface.co/roberta-large/resolve/main/vocab.json",
        "roberta-large-mnli": "https://huggingface.co/roberta-large-mnli/resolve/main/vocab.json",
        "distilroberta-base": "https://huggingface.co/distilroberta-base/resolve/main/vocab.json",
        "roberta-base-openai-detector": "https://huggingface.co/roberta-base-openai-detector/resolve/main/vocab.json",
        "roberta-large-openai-detector": "https://huggingface.co/roberta-large-openai-detector/resolve/main/vocab.json",
    },
    "merges_file": {
        "roberta-base": "https://huggingface.co/roberta-base/resolve/main/merges.txt",
        "roberta-large": "https://huggingface.co/roberta-large/resolve/main/merges.txt",
        "roberta-large-mnli": "https://huggingface.co/roberta-large-mnli/resolve/main/merges.txt",
        "distilroberta-base": "https://huggingface.co/distilroberta-base/resolve/main/merges.txt",
        "roberta-base-openai-detector": "https://huggingface.co/roberta-base-openai-detector/resolve/main/merges.txt",
        "roberta-large-openai-detector": "https://huggingface.co/roberta-large-openai-detector/resolve/main/merges.txt",
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "roberta-base": 512,
    "roberta-large": 512,
    "roberta-large-mnli": 512,
    "distilroberta-base": 512,
    "roberta-base-openai-detector": 512,
    "roberta-large-openai-detector": 512,
}


class RobertaTokenizer(GPT2Tokenizer):
    """
    Constructs a RoBERTa tokenizer, derived from the GPT-2 tokenizer, using byte-level Byte-Pair-Encoding.

    This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
    be encoded differently whether it is at the beginning of the sentence (without space) or not:

    ::

        >>> from transformers import RobertaTokenizer
        >>> tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
        >>> tokenizer("Hello world")['input_ids']
        [0, 31414, 232, 328, 2]
        >>> tokenizer(" Hello world")['input_ids']
        [0, 20920, 232, 2]

    You can get around that behavior by passing ``add_prefix_space=True`` when instantiating this tokenizer or when you
    call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.

    .. note::

        When used with ``is_split_into_words=True``, this tokenizer will add a space before each word (even the first
        one).

    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods.
    Users should refer to this superclass for more information regarding those methods.

    Args:
        vocab_file (:obj:`str`):
            Path to the vocabulary file.
        merges_file (:obj:`str`):
            Path to the merges file.
        errors (:obj:`str`, `optional`, defaults to :obj:`"replace"`):
            Paradigm to follow when decoding bytes to UTF-8. See `bytes.decode
            <https://docs.python.org/3/library/stdtypes.html#bytes.decode>`__ for more information.
        bos_token (:obj:`str`, `optional`, defaults to :obj:`"<s>"`):
            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.

            .. note::

                When building a sequence using special tokens, this is not the token that is used for the beginning of
                sequence. The token used is the :obj:`cls_token`.
        eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
            The end of sequence token.

            .. note::

                When building a sequence using special tokens, this is not the token that is used for the end of
                sequence. The token used is the :obj:`sep_token`.
        sep_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
            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.
        cls_token (:obj:`str`, `optional`, defaults to :obj:`"<s>"`):
            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.
        unk_token (:obj:`str`, `optional`, defaults to :obj:`"<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.
        pad_token (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
            The token used for padding, for example when batching sequences of different lengths.
        mask_token (:obj:`str`, `optional`, defaults to :obj:`"<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.
        add_prefix_space (:obj:`bool`, `optional`, defaults to :obj:`False`):
            Whether or not to add an initial space to the input. This allows to treat the leading word just as any
            other word. (RoBERTa tokenizer detect beginning of words by the preceding space).
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file,
        merges_file,
        errors="replace",
        bos_token="<s>",
        eos_token="</s>",
        sep_token="</s>",
        cls_token="<s>",
        unk_token="<unk>",
        pad_token="<pad>",
        mask_token="<mask>",
        add_prefix_space=False,
        **kwargs
    ):
        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
        sep_token = AddedToken(sep_token, lstrip=False, rstrip=False) if isinstance(sep_token, str) else sep_token
        cls_token = AddedToken(cls_token, lstrip=False, rstrip=False) if isinstance(cls_token, str) else cls_token
        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token

        # Mask token behave like a normal word, i.e. include the space before it
        mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token

        super().__init__(
            vocab_file=vocab_file,
            merges_file=merges_file,
            errors=errors,
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            sep_token=sep_token,
            cls_token=cls_token,
            pad_token=pad_token,
            mask_token=mask_token,
            add_prefix_space=add_prefix_space,
            **kwargs,
        )

    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 RoBERTa sequence has the following format:

        - single sequence: ``<s> X </s>``
        - pair of sequences: ``<s> A </s></s> B </s>``

        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.
        """
        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 + 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 (: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:
            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 None:
            return [1] + ([0] * len(token_ids_0)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [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. RoBERTa does not
        make use of token type ids, therefore a list of zeros is returned.

        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 zeros.
        """
        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 + sep + token_ids_1 + sep) * [0]

    def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
        add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
        if (is_split_into_words or add_prefix_space) and (len(text) > 0 and not text[0].isspace()):
            text = " " + text
        return (text, kwargs)