KoRean based Bert pre-trained (KR-BERT)

This is a release of Korean-specific, small-scale BERT models with comparable or better performances developed by Computational Linguistics Lab at Seoul National University, referenced in KR-BERT: A Small-Scale Korean-Specific Language Model.

<br>

Vocab, Parameters and Data

<br>

Sub-character

Korean text is basically represented with Hangul syllable characters, which can be decomposed into sub-characters, or graphemes. To accommodate such characteristics, we trained a new vocabulary and BERT model on two different representations of a corpus: syllable characters and sub-characters.

In case of using our sub-character model, you should preprocess your data with the code below.

import torch
from transformers import BertConfig, BertModel, BertForPreTraining, BertTokenizer
from unicodedata import normalize

tokenizer_krbert = BertTokenizer.from_pretrained('/path/to/vocab_file.txt', do_lower_case=False)

# convert a string into sub-char
def to_subchar(string):
    return normalize('NFKD', string)

sentence = '토크나이저 예시입니다.'
print(tokenizer_krbert.tokenize(to_subchar(sentence)))

Tokenization

BidirectionalWordPiece Tokenizer

We use the BidirectionalWordPiece model to reduce search costs while maintaining the possibility of choice. This model applies BPE in both forward and backward directions to obtain two candidates and chooses the one that has a higher frequency.

<br>

Models

<!--

tensorflow

• BERT tokenizer, character model (download)
• BidirectionalWordPiece tokenizer, character model (download)
• BERT tokenizer, sub-character model (download)
• BidirectionalWordPiece tokenizer, sub-character model (download)

pytorch

• BERT tokenizer, character model (download)
• BidirectionalWordPiece tokenizer, character model (download)
• BERT tokenizer, sub-character model (download)
• BidirectionalWordPiece tokenizer, sub-character model (download) -->

<br>

Requirements

• transformers == 2.1.1
• tensorflow < 2.0

<br>

Downstream tasks

Naver Sentiment Movie Corpus (NSMC)

• If you want to use the sub-character version of our models, let the subchar argument be True.

• And you can use the original BERT WordPiece tokenizer by entering bert for the tokenizer argument, and if you use ranked you can use our BidirectionalWordPiece tokenizer.

• tensorflow: After downloading our pretrained models, put them in a models directory in the krbert_tensorflow directory.

• pytorch: After downloading our pretrained models, put them in a pretrained directory in the krbert_pytorch directory.

# pytorch
python3 train.py --subchar {True, False} --tokenizer {bert, ranked}

# tensorflow
python3 run_classifier.py \
  --task_name=NSMC \
  --subchar={True, False} \
  --tokenizer={bert, ranked} \
  --do_train=true \
  --do_eval=true \
  --do_predict=true \
  --do_lower_case=False\
  --max_seq_length=128 \
  --train_batch_size=128 \
  --learning_rate=5e-05 \
  --num_train_epochs=5.0 \
  --output_dir={output_dir}

The pytorch code structure refers to that of https://github.com/aisolab/nlp_implementation .

<br>

NSMC Acc.

<br>

Citation

If you use these models, please cite the following paper:

@article{lee2020krbert,
    title={KR-BERT: A Small-Scale Korean-Specific Language Model},
    author={Sangah Lee and Hansol Jang and Yunmee Baik and Suzi Park and Hyopil Shin},
    year={2020},
    journal={ArXiv},
    volume={abs/2008.03979}
  }

<br>

Contacts

nlp.snu@gmail.com