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

Anonymous

Paper Link: https://openreview.net/forum?id=d61NGy9bquC

Paper Type: Short paper (up to four pages of content + unlimited references and appendices)

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 \url{https://github.com/csebuetnlp/banglabert} to advance Bangla NLP.

Presentation Mode: This paper will be presented virtually

Virtual Presentation Timezone: UTC+6

Copyright Consent Signature (type Name Or NA If Not Transferrable): Abhik Bhattacharjee

Copyright Consent Name And Address: 38/9/A, Palashnagar, Mirpur-11, Dhaka