Source code for transformers.models.mbart.tokenization_mbart

# coding=utf-8
# Copyright 2020 The Facebook AI Research 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
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.

from typing import List, Optional

from ...file_utils import add_start_docstrings
from ...tokenization_utils import BatchEncoding
from ...tokenization_utils_base import PREPARE_SEQ2SEQ_BATCH_DOCSTRING
from ...utils import logging
from ..xlm_roberta.tokenization_xlm_roberta import XLMRobertaTokenizer

logger = logging.get_logger(__name__)

_all_mbart_models = ["facebook/mbart-large-en-ro", "facebook/mbart-large-cc25"]
SPM_URL = ""


[docs]class MBartTokenizer(XLMRobertaTokenizer): """ Construct an MBART tokenizer. :class:`~transformers.MBartTokenizer` is a subclass of :class:`~transformers.XLMRobertaTokenizer` and adds a new :meth:`~transformers.MBartTokenizer.prepare_seq2seq_batch` Refer to superclass :class:`~transformers.XLMRobertaTokenizer` for usage examples and documentation concerning the initialization parameters and other methods. .. warning:: ``prepare_seq2seq_batch`` should be used to encode inputs. Other tokenizer methods like ``encode`` do not work properly. The tokenization method is ``<tokens> <eos> <language code>`` for source language documents, and ``<language code> <tokens> <eos>``` for target language documents. Examples:: >>> from transformers import MBartTokenizer >>> tokenizer = MBartTokenizer.from_pretrained('facebook/mbart-large-en-ro') >>> example_english_phrase = " UN Chief Says There Is No Military Solution in Syria" >>> expected_translation_romanian = "Şeful ONU declară că nu există o soluţie militară în Siria" >>> batch: dict = tokenizer.prepare_seq2seq_batch( ... example_english_phrase, src_lang="en_XX", tgt_lang="ro_RO", tgt_texts=expected_translation_romanian, return_tensors="pt" ... ) """ vocab_files_names = {"vocab_file": "sentencepiece.bpe.model"} max_model_input_sizes = {m: 1024 for m in _all_mbart_models} pretrained_vocab_files_map = {"vocab_file": {m: SPM_URL for m in _all_mbart_models}} prefix_tokens: List[int] = [] suffix_tokens: List[int] = [] def __init__(self, *args, tokenizer_file=None, **kwargs): super().__init__(*args, tokenizer_file=tokenizer_file, **kwargs) self.sp_model_size = len(self.sp_model) self.lang_code_to_id = { code: self.sp_model_size + i + self.fairseq_offset for i, code in enumerate(FAIRSEQ_LANGUAGE_CODES) } self.id_to_lang_code = {v: k for k, v in self.lang_code_to_id.items()} self.cur_lang_code = self.lang_code_to_id["en_XX"] self.fairseq_tokens_to_ids["<mask>"] = len(self.sp_model) + len(self.lang_code_to_id) + self.fairseq_offset self.fairseq_tokens_to_ids.update(self.lang_code_to_id) self.fairseq_ids_to_tokens = {v: k for k, v in self.fairseq_tokens_to_ids.items()} self._additional_special_tokens = list(self.lang_code_to_id.keys()) self.set_src_lang_special_tokens(kwargs.get("src_lang", "en_XX")) @property def vocab_size(self): return len(self.sp_model) + len(self.lang_code_to_id) + self.fairseq_offset + 1 # Plus 1 for the mask token 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)) prefix_ones = [1] * len(self.prefix_tokens) suffix_ones = [1] * len(self.suffix_tokens) if token_ids_1 is None: return prefix_ones + ([0] * len(token_ids_0)) + suffix_ones return prefix_ones + ([0] * len(token_ids_0)) + ([0] * len(token_ids_1)) + suffix_ones
[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. An MBART sequence has the following format, where ``X`` represents the sequence: - ``input_ids`` (for encoder) ``X [eos, src_lang_code]`` - ``decoder_input_ids``: (for decoder) ``X [eos, tgt_lang_code]`` BOS is never used. Pairs of sequences are not the expected use case, but they will be handled without a separator. 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.prefix_tokens + token_ids_0 + self.suffix_tokens # We don't expect to process pairs, but leave the pair logic for API consistency return self.prefix_tokens + token_ids_0 + token_ids_1 + self.suffix_tokens
[docs] @add_start_docstrings(PREPARE_SEQ2SEQ_BATCH_DOCSTRING) def prepare_seq2seq_batch( self, src_texts: List[str], src_lang: str = "en_XX", tgt_texts: Optional[List[str]] = None, tgt_lang: str = "ro_RO", max_length: Optional[int] = None, max_target_length: Optional[int] = None, truncation: bool = True, padding: str = "longest", return_tensors: Optional[str] = None, add_prefix_space: bool = False, # ignored **kwargs, ) -> BatchEncoding: if max_length is None: max_length = self.model_max_length self.set_src_lang_special_tokens(src_lang) model_inputs: BatchEncoding = self( src_texts, add_special_tokens=True, return_tensors=return_tensors, max_length=max_length, padding=padding, truncation=truncation, **kwargs, ) if tgt_texts is None: return model_inputs # Process tgt_texts if max_target_length is None: max_target_length = max_length self.set_tgt_lang_special_tokens(tgt_lang) labels = self( tgt_texts, add_special_tokens=True, return_tensors=return_tensors, padding=padding, max_length=max_target_length, truncation=True, **kwargs, )["input_ids"] model_inputs["labels"] = labels self.set_src_lang_special_tokens(src_lang) # sets to src_lang return model_inputs
def set_src_lang_special_tokens(self, src_lang) -> None: """Reset the special tokens to the source lang setting. No prefix and suffix=[eos, src_lang_code].""" self.cur_lang_code = self.lang_code_to_id[src_lang] self.prefix_tokens = [] self.suffix_tokens = [self.eos_token_id, self.cur_lang_code] def set_tgt_lang_special_tokens(self, lang: str) -> None: """Reset the special tokens to the target language setting. No prefix and suffix=[eos, tgt_lang_code].""" self.cur_lang_code = self.lang_code_to_id[lang] self.prefix_tokens = [] self.suffix_tokens = [self.eos_token_id, self.cur_lang_code]