@inproceedings{sayed-etal-2026-bansuite,
title = "{B}an{S}uite: A Unified Toolkit and Software Platform for Low-Resource {NLP} in {B}angla",
author = "Sayed, Md. Abu and
Khan, Faisal Ahamed and
Tuli, Jannatul Ferdous and
Mohammed, Nabeel and
Amin, Mohammad Ruhul and
Rashid, Mohammad Mamun Or",
editor = "Croce, Danilo and
Leidner, Jochen and
Moosavi, Nafise Sadat",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
month = mar,
year = "2026",
address = "Rabat, Marocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-demo.44/",
pages = "609--620",
ISBN = "979-8-89176-382-1",
abstract = "Bangla is one of the world{'}s most widely spoken languages, yet it remains significantly under-resourced in natural language processing (NLP). Existing efforts have focused on isolated tasks such as Part-of-Speech (POS) tagging and Named Entity Recognition (NER), but comprehensive, integrated systems for core NLP tasks including Shallow Parsing and Dependency Parsing are largely absent. To address this gap, we present BanSuite, a unified Bangla NLP ecosystem developed under the EBLICT project. BanSuite combines a large-scale, manually annotated Bangla Treebank with high-quality pretrained models for POS tagging, NER, shallow parsing, and dependency parsing, achieving strong in-domain baseline performance (POS: 90.16 F1, NER: 90.11 F1, SP: 86.92 F1, DP: 90.27 UAS). The system is accessible through a Python toolkit (Bkit) and a Web Application, providing both researchers and non-technical users with robust NLP functionalities, including tokenization, normalization, lemmatization, and syntactic parsing. In benchmarking against existing Bangla NLP tools and multilingual Large Language Models (LLMs), BanSuite demonstrates superior task performance while maintaining high efficiency in resource usage. By offering the first comprehensive, open, and integrated NLP platform for Bangla, BanSuite lays a scalable foundation for research, application development, and further advancement of low-resource language technologies. A demonstration video is provided to illustrate the system{'}s functionality in https://youtu.be/3pcfiUQfCoA"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sayed-etal-2026-bansuite">
<titleInfo>
<title>BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Abu</namePart>
<namePart type="family">Sayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="given">Ahamed</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jannatul</namePart>
<namePart type="given">Ferdous</namePart>
<namePart type="family">Tuli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nabeel</namePart>
<namePart type="family">Mohammed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Mamun</namePart>
<namePart type="given">Or</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Croce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jochen</namePart>
<namePart type="family">Leidner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Marocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-382-1</identifier>
</relatedItem>
<abstract>Bangla is one of the world’s most widely spoken languages, yet it remains significantly under-resourced in natural language processing (NLP). Existing efforts have focused on isolated tasks such as Part-of-Speech (POS) tagging and Named Entity Recognition (NER), but comprehensive, integrated systems for core NLP tasks including Shallow Parsing and Dependency Parsing are largely absent. To address this gap, we present BanSuite, a unified Bangla NLP ecosystem developed under the EBLICT project. BanSuite combines a large-scale, manually annotated Bangla Treebank with high-quality pretrained models for POS tagging, NER, shallow parsing, and dependency parsing, achieving strong in-domain baseline performance (POS: 90.16 F1, NER: 90.11 F1, SP: 86.92 F1, DP: 90.27 UAS). The system is accessible through a Python toolkit (Bkit) and a Web Application, providing both researchers and non-technical users with robust NLP functionalities, including tokenization, normalization, lemmatization, and syntactic parsing. In benchmarking against existing Bangla NLP tools and multilingual Large Language Models (LLMs), BanSuite demonstrates superior task performance while maintaining high efficiency in resource usage. By offering the first comprehensive, open, and integrated NLP platform for Bangla, BanSuite lays a scalable foundation for research, application development, and further advancement of low-resource language technologies. A demonstration video is provided to illustrate the system’s functionality in https://youtu.be/3pcfiUQfCoA</abstract>
<identifier type="citekey">sayed-etal-2026-bansuite</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-demo.44/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>609</start>
<end>620</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla
%A Sayed, Md. Abu
%A Khan, Faisal Ahamed
%A Tuli, Jannatul Ferdous
%A Mohammed, Nabeel
%A Amin, Mohammad Ruhul
%A Rashid, Mohammad Mamun Or
%Y Croce, Danilo
%Y Leidner, Jochen
%Y Moosavi, Nafise Sadat
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-382-1
%F sayed-etal-2026-bansuite
%X Bangla is one of the world’s most widely spoken languages, yet it remains significantly under-resourced in natural language processing (NLP). Existing efforts have focused on isolated tasks such as Part-of-Speech (POS) tagging and Named Entity Recognition (NER), but comprehensive, integrated systems for core NLP tasks including Shallow Parsing and Dependency Parsing are largely absent. To address this gap, we present BanSuite, a unified Bangla NLP ecosystem developed under the EBLICT project. BanSuite combines a large-scale, manually annotated Bangla Treebank with high-quality pretrained models for POS tagging, NER, shallow parsing, and dependency parsing, achieving strong in-domain baseline performance (POS: 90.16 F1, NER: 90.11 F1, SP: 86.92 F1, DP: 90.27 UAS). The system is accessible through a Python toolkit (Bkit) and a Web Application, providing both researchers and non-technical users with robust NLP functionalities, including tokenization, normalization, lemmatization, and syntactic parsing. In benchmarking against existing Bangla NLP tools and multilingual Large Language Models (LLMs), BanSuite demonstrates superior task performance while maintaining high efficiency in resource usage. By offering the first comprehensive, open, and integrated NLP platform for Bangla, BanSuite lays a scalable foundation for research, application development, and further advancement of low-resource language technologies. A demonstration video is provided to illustrate the system’s functionality in https://youtu.be/3pcfiUQfCoA
%U https://aclanthology.org/2026.eacl-demo.44/
%P 609-620
Markdown (Informal)
[BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla](https://aclanthology.org/2026.eacl-demo.44/) (Sayed et al., EACL 2026)
ACL
- Md. Abu Sayed, Faisal Ahamed Khan, Jannatul Ferdous Tuli, Nabeel Mohammed, Mohammad Ruhul Amin, and Mohammad Mamun Or Rashid. 2026. BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 609–620, Rabat, Marocco. Association for Computational Linguistics.