Bangla-BERT: Transformer-Based Efficient Model for Transfer Learning and Language Understanding

M. Kowsher, Abdullah As Sami, Nusrat Jahan Prottasha, Mohammad Shamsul Arefin*, Pranab Kumar Dhar, Takeshi Koshiba

*この研究の対応する著者

研究成果: Article査読

1 被引用数 (Scopus)

抄録

The advent of pre-trained language models has directed a new era of Natural Language Processing (NLP), enabling us to create powerful language models. Among these models, Transformer-based models like BERT have grown in popularity due to their cutting-edge effectiveness. However, these models heavily rely on resource-intensive languages, forcing other languages into multilingual models(mBERT). The two fundamental challenges with mBERT become significantly more challenging in a resource-constrained language like Bangla. It was trained on a limited and organized dataset and contained weights for all other languages. Besides, current research on other languages suggests that a language-specific BERT model will exceed multilingual ones. This paper introduces Bangla-BERT,a a monolingual BERT model for the Bangla language. Despite the limited data available for NLP tasks in Bangla, we perform pre-training on the largest Bangla language model dataset, BanglaLM, which we constructed using 40 GB of text data. Bangla-BERT achieves the highest results in all datasets and vastly improves the state-of-the-art performance in binary linguistic classification, multilabel extraction, and named entity recognition, outperforming multilingual BERT and other previous research. The pre-trained model is assessed against several non-contextual models such as Bangla fasttext and word2vec the downstream tasks. Finally, this model is evaluated by transfer learning based on hybrid deep learning models such as LSTM, CNN, and CRF in NER, and it is observed that Bangla-BERT outperforms state-of-the-art methods. The proposed Bangla-BERT model is assessed by using benchmark datasets, including Banfakenews, Sentiment Analysis on Bengali News Comments, and Cross-lingual Sentiment Analysis in Bengali. Finally, it is concluded that Bangla-BERT surpasses all prior state-of-the-art results by 3.52%, 2.2%, and 5.3%.

本文言語English
ページ(範囲)91855-91870
ページ数16
ジャーナルIEEE Access
10
DOI
出版ステータスPublished - 2022

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 材料科学(全般)
  • 工学(全般)
  • 電子工学および電気工学

フィンガープリント

「Bangla-BERT: Transformer-Based Efficient Model for Transfer Learning and Language Understanding」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル