
Academic lab · Dhaka, Bangladesh
BUET CSE NLP Group
A BUET research group on low-resource Bangla NLP that releases BanglaBERT, BanglaT5 and the XL-Sum summarisation dataset.
Dhaka, Bangladesh
- Type
- Academic lab
- Based in
- Dhaka, Bangladesh
- Key papers
- 4
- Featured projects
- 8
About
The CSE NLP group at Bangladesh University of Engineering and Technology works on machine translation, multilingual NLP and language understanding. Its faculty include Rifat Shahriyar, M. Sohel Rahman and Anindya Iqbal.
It open-sourced BanglaBERT in 2021 and BanglaT5 in 2022, and published XL-Sum, a 44-language summarisation dataset, at ACL 2021 Findings.
Mission and ambitionsThe group aims to provide open models and benchmarks for Bangla.
Known for
- 01
BanglaBERT
- 02
BanglaT5
- 03
XL-Sum dataset
Milestones
- 2020
Bengali-English MT datasets
Aligner ensembling and new datasets for Bengali-English translation were published.
- 2021
XL-Sum published
A summarisation dataset in 44 languages, at Findings of ACL 2021.
- 2021
BanglaBERT open-sourced
A Bangla language model, later published in Findings of NAACL 2022.
- 2022
BanglaT5 released
A Bangla sequence-to-sequence model.
Open source
XL-Sum code, data, models.
BanglaBERT release.
Bangla NMT.
BanglaT5 release.
BanglaBERT.
Multilingual summarizer.
- csebuetnlp/xlsumdataset
XL-Sum.
- csebuetnlp/CrossSumdataset
Cross-lingual summarization.
Research papers
Notable releases
Openness
Open models and datasets.
People
- Rifat ShahriyarProfessor, BUET
- M. Sohel RahmanProfessor, BUET
- Anindya IqbalProfessor, BUET
- Tahmid HasanResearcher; lead author of XL-Sum
- Abhik BhattacharjeeResearch assistant; lead author of BanglaBERT and BanglaT5
Listed from the lab's own pages and public profiles.
Contact and community
The group site csebuetnlp.github.io links its GitHub and papers; GitHub issues are the open route.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



