BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla

Abhik Bhattacharjee, Tahmid Hasan, Wasi Ahmad, Kazi Samin Mubasshir, Md Saiful Islam, Anindya Iqbal, M. Sohel Rahman, Rifat Shahriyar


Abstract
In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature. To pretrain BanglaBERT, we collect 27.5 GB of Bangla pretraining data (dubbed ‘Bangla2B+’) by crawling 110 popular Bangla sites. We introduce two downstream task datasets on natural language inference and question answering and benchmark on four diverse NLU tasks covering text classification, sequence labeling, and span prediction. In the process, we bring them under the first-ever Bangla Language Understanding Benchmark (BLUB). BanglaBERT achieves state-of-the-art results outperforming multilingual and monolingual models. We are making the models, datasets, and a leaderboard publicly available at https://github.com/csebuetnlp/banglabert to advance Bangla NLP.
Anthology ID:
2022.findings-naacl.98
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1318–1327
Language:
URL:
https://aclanthology.org/2022.findings-naacl.98
DOI:
10.18653/v1/2022.findings-naacl.98
Bibkey:
Cite (ACL):
Abhik Bhattacharjee, Tahmid Hasan, Wasi Ahmad, Kazi Samin Mubasshir, Md Saiful Islam, Anindya Iqbal, M. Sohel Rahman, and Rifat Shahriyar. 2022. BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1318–1327, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla (Bhattacharjee et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.98.pdf
Video:
 https://aclanthology.org/2022.findings-naacl.98.mp4
Code
 csebuetnlp/banglabert
Data
MultiCoNERSentNoBTyDiQA