@inproceedings{bhuiyan-etal-2025-bhasabodh,
title = "{B}hasa{B}odh: Bridging {B}angla Dialects and {R}omanized Forms through Machine Translation",
author = "Bhuiyan, Md. Tofael Ahmed and
Rahman, Md. Abdur and
Masum, Abdul Kadar Muhammad",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Hassan, Naeemul and
Prince, Enamul Hoque and
Tasnim, Mohiuddin and
Rony, Md Rashad Al Hasan and
Rahman, Md Tahmid Rahman",
booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.banglalp-1.9/",
pages = "113--118",
ISBN = "979-8-89176-314-2",
abstract = "While machine translation has made significant strides for high-resource languages, many regional languages and their dialects, such as the Bangla variants Chittagong and Sylhet, remain underserved. Existing resources are often insufficient for robust sentence-level evaluation and overlook the widespread real-world practice of romanization, the common practice of typing native languages using the Latin script in digital communication. To address these gaps, we introduce BhasaBodh, a comprehensive benchmark for Bangla dialectal machine translation. We construct and release a sentence-level parallel dataset for Chittagong and Sylhet dialects aligned with Standard Bangla and English, create a novel romanized version of the dialectal data to facilitate evaluation in realistic multi-script scenarios, and provide the first comprehensive performance baselines by fine-tuning two powerful multilingual models, NLLB-200 and mBART-50, on seven distinct translation tasks. Our experiments reveal that mBART-50 consistently outperforms NLLB-200 on most dialectal and romanized tasks, achieving a BLEU score as high as 87.44 on the Romanized-to-Standard Bangla normalization task. However, complex cross-lingual and cross-script translation remains a significant challenge. BhasaBodh lays the groundwork for future research in low-resource dialectal NLP, offering a valuable resource for developing more inclusive and practical translation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhuiyan-etal-2025-bhasabodh">
<titleInfo>
<title>BhasaBodh: Bridging Bangla Dialects and Romanized Forms through Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Tofael</namePart>
<namePart type="given">Ahmed</namePart>
<namePart type="family">Bhuiyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Abdur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="given">Kadar</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="family">Masum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naeemul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="given">Hoque</namePart>
<namePart type="family">Prince</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohiuddin</namePart>
<namePart type="family">Tasnim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rashad</namePart>
<namePart type="given">Al</namePart>
<namePart type="given">Hasan</namePart>
<namePart type="family">Rony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-314-2</identifier>
</relatedItem>
<abstract>While machine translation has made significant strides for high-resource languages, many regional languages and their dialects, such as the Bangla variants Chittagong and Sylhet, remain underserved. Existing resources are often insufficient for robust sentence-level evaluation and overlook the widespread real-world practice of romanization, the common practice of typing native languages using the Latin script in digital communication. To address these gaps, we introduce BhasaBodh, a comprehensive benchmark for Bangla dialectal machine translation. We construct and release a sentence-level parallel dataset for Chittagong and Sylhet dialects aligned with Standard Bangla and English, create a novel romanized version of the dialectal data to facilitate evaluation in realistic multi-script scenarios, and provide the first comprehensive performance baselines by fine-tuning two powerful multilingual models, NLLB-200 and mBART-50, on seven distinct translation tasks. Our experiments reveal that mBART-50 consistently outperforms NLLB-200 on most dialectal and romanized tasks, achieving a BLEU score as high as 87.44 on the Romanized-to-Standard Bangla normalization task. However, complex cross-lingual and cross-script translation remains a significant challenge. BhasaBodh lays the groundwork for future research in low-resource dialectal NLP, offering a valuable resource for developing more inclusive and practical translation systems.</abstract>
<identifier type="citekey">bhuiyan-etal-2025-bhasabodh</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.9/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>113</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BhasaBodh: Bridging Bangla Dialects and Romanized Forms through Machine Translation
%A Bhuiyan, Md. Tofael Ahmed
%A Rahman, Md. Abdur
%A Masum, Abdul Kadar Muhammad
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Hassan, Naeemul
%Y Prince, Enamul Hoque
%Y Tasnim, Mohiuddin
%Y Rony, Md Rashad Al Hasan
%Y Rahman, Md Tahmid Rahman
%S Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-314-2
%F bhuiyan-etal-2025-bhasabodh
%X While machine translation has made significant strides for high-resource languages, many regional languages and their dialects, such as the Bangla variants Chittagong and Sylhet, remain underserved. Existing resources are often insufficient for robust sentence-level evaluation and overlook the widespread real-world practice of romanization, the common practice of typing native languages using the Latin script in digital communication. To address these gaps, we introduce BhasaBodh, a comprehensive benchmark for Bangla dialectal machine translation. We construct and release a sentence-level parallel dataset for Chittagong and Sylhet dialects aligned with Standard Bangla and English, create a novel romanized version of the dialectal data to facilitate evaluation in realistic multi-script scenarios, and provide the first comprehensive performance baselines by fine-tuning two powerful multilingual models, NLLB-200 and mBART-50, on seven distinct translation tasks. Our experiments reveal that mBART-50 consistently outperforms NLLB-200 on most dialectal and romanized tasks, achieving a BLEU score as high as 87.44 on the Romanized-to-Standard Bangla normalization task. However, complex cross-lingual and cross-script translation remains a significant challenge. BhasaBodh lays the groundwork for future research in low-resource dialectal NLP, offering a valuable resource for developing more inclusive and practical translation systems.
%U https://aclanthology.org/2025.banglalp-1.9/
%P 113-118
Markdown (Informal)
[BhasaBodh: Bridging Bangla Dialects and Romanized Forms through Machine Translation](https://aclanthology.org/2025.banglalp-1.9/) (Bhuiyan et al., BanglaLP 2025)
ACL