BARTpho
Overview
The BARTpho model was proposed in BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese by Nguyen Luong Tran, Duong Minh Le and Dat Quoc Nguyen.
The abstract from the paper is the following:
We present BARTpho with two versions — BARTpho_word and BARTpho_syllable — the first public large-scale monolingual sequence-to-sequence models pre-trained for Vietnamese. Our BARTpho uses the “large” architecture and pre-training scheme of the sequence-to-sequence denoising model BART, thus especially suitable for generative NLP tasks. Experiments on a downstream task of Vietnamese text summarization show that in both automatic and human evaluations, our BARTpho outperforms the strong baseline mBART and improves the state-of-the-art. We release BARTpho to facilitate future research and applications of generative Vietnamese NLP tasks.
This model was contributed by dqnguyen. The original code can be found here.
Usage example
>>> import torch
>>> from transformers import AutoModel, AutoTokenizer
>>> bartpho = AutoModel.from_pretrained("vinai/bartpho-syllable")
>>> tokenizer = AutoTokenizer.from_pretrained("vinai/bartpho-syllable")
>>> line = "Chúng tôi là những nghiên cứu viên."
>>> input_ids = tokenizer(line, return_tensors="pt")
>>> with torch.no_grad():
... features = bartpho(**input_ids) # Models outputs are now tuples
>>> # With TensorFlow 2.0+:
>>> from transformers import TFAutoModel
>>> bartpho = TFAutoModel.from_pretrained("vinai/bartpho-syllable")
>>> input_ids = tokenizer(line, return_tensors="tf")
>>> features = bartpho(**input_ids)Usage tips
- Following mBART, BARTpho uses the “large” architecture of BART with an additional layer-normalization layer on top of both the encoder and decoder. Thus, usage examples in the documentation of BART, when adapting to use with BARTpho, should be adjusted by replacing the BART-specialized classes with the mBART-specialized counterparts. For example:
>>> from transformers import MBartForConditionalGeneration
>>> bartpho = MBartForConditionalGeneration.from_pretrained("vinai/bartpho-syllable")
>>> TXT = "Chúng tôi là <mask> nghiên cứu viên."
>>> input_ids = tokenizer([TXT], return_tensors="pt")["input_ids"]
>>> logits = bartpho(input_ids).logits
>>> masked_index = (input_ids[0] == tokenizer.mask_token_id).nonzero().item()
>>> probs = logits[0, masked_index].softmax(dim=0)
>>> values, predictions = probs.topk(5)
>>> print(tokenizer.decode(predictions).split())- This implementation is only for tokenization: “monolingual_vocab_file” consists of Vietnamese-specialized types extracted from the pre-trained SentencePiece model “vocab_file” that is available from the multilingual XLM-RoBERTa. Other languages, if employing this pre-trained multilingual SentencePiece model “vocab_file” for subword segmentation, can reuse BartphoTokenizer with their own language-specialized “monolingual_vocab_file”.
BartphoTokenizer
class transformers.BartphoTokenizer
< source >( vocab_file monolingual_vocab_file bos_token = '<s>' eos_token = '</s>' sep_token = '</s>' cls_token = '<s>' unk_token = '<unk>' pad_token = '<pad>' mask_token = '<mask>' sp_model_kwargs: Optional = None **kwargs )
Parameters
- vocab_file (
str) — Path to the vocabulary file. This vocabulary is the pre-trained SentencePiece model available from the multilingual XLM-RoBERTa, also used in mBART, consisting of 250K types. - monolingual_vocab_file (
str) — Path to the monolingual vocabulary file. This monolingual vocabulary consists of Vietnamese-specialized types extracted from the multilingual vocabulary vocab_file of 250K types. - bos_token (
str, optional, defaults to"<s>") — The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.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
cls_token. - eos_token (
str, optional, defaults to"</s>") — The end of sequence token.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
sep_token. - sep_token (
str, optional, defaults to"</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 (
str, optional, defaults to"<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 (
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. - pad_token (
str, optional, defaults to"<pad>") — The token used for padding, for example when batching sequences of different lengths. - 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. - sp_model_kwargs (
dict, optional) — Will be passed to theSentencePieceProcessor.__init__()method. The Python wrapper for SentencePiece can be used, among other things, to set:-
enable_sampling: Enable subword regularization. -
nbest_size: Sampling parameters for unigram. Invalid for BPE-Dropout.nbest_size = {0,1}: No sampling is performed.nbest_size > 1: samples from the nbest_size results.nbest_size < 0: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm.
-
alpha: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout.
-
- sp_model (
SentencePieceProcessor) — The SentencePiece processor that is used for every conversion (string, tokens and IDs).
Adapted from XLMRobertaTokenizer. Based on SentencePiece.
This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.
build_inputs_with_special_tokens
< source >( token_ids_0: List token_ids_1: Optional = None ) → List[int]
Parameters
- 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 with the appropriate special tokens.
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. An BARTPho sequence has the following format:
- single sequence:
<s> X </s> - pair of sequences:
<s> A </s></s> B </s>
Converts a sequence of tokens (strings for sub-words) in a single string.
create_token_type_ids_from_sequences
< source >( token_ids_0: List token_ids_1: Optional = None ) → List[int]
Create a mask from the two sequences passed to be used in a sequence-pair classification task. BARTPho does not make use of token type ids, therefore a list of zeros is returned.
get_special_tokens_mask
< source >( token_ids_0: List token_ids_1: Optional = None already_has_special_tokens: bool = False ) → List[int]
Parameters
- 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 toFalse) — 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.
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.