@inproceedings{rahman-etal-2025-chakmabridge,
title = "{C}hakma{B}ridge: A Five-Way Parallel Corpus for Navigating the Script Divide in an Endangered Language",
author = "Rahman, Md. Abdur and
Bhuiyan, Md. Tofael Ahmed 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-1.21/",
pages = "259--265",
ISBN = "979-8-89176-314-2",
abstract = "The advancement of NLP technologies for low-resource and endangered languages is critically hindered by the scarcity of high-quality, parallel corpora. This is particularly true for languages like Chakma, which also faces the challenge of prevalent non-standard, romanized script usage in digital communication. To address this, we introduce ChakmaBridge, the first five-way parallel corpus for Chakma, containing 807 sentences aligned across English, Standard Bangla, Bengali-script Chakma, Romanized Bangla, and Romanized Chakma. Our dataset is created by augmenting the MELD corpus with LLM-generated romanizations that are rigorously validated by native speakers. We establish robust machine translation baselines across six diverse language and script pairs. Our experiments reveal that a multilingual training approach, combining English and Bangla as source languages, yields a dramatic performance increase, achieving a BLEU score of 0.5228 for Chakma translation, a 124{\%} relative improvement over the best bilingual model. We release ChakmaBridge to facilitate research in low-resource MT and aid in the digital preservation of this endangered language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2025-chakmabridge">
<titleInfo>
<title>ChakmaBridge: A Five-Way Parallel Corpus for Navigating the Script Divide in an Endangered Language</title>
</titleInfo>
<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">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">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>The advancement of NLP technologies for low-resource and endangered languages is critically hindered by the scarcity of high-quality, parallel corpora. This is particularly true for languages like Chakma, which also faces the challenge of prevalent non-standard, romanized script usage in digital communication. To address this, we introduce ChakmaBridge, the first five-way parallel corpus for Chakma, containing 807 sentences aligned across English, Standard Bangla, Bengali-script Chakma, Romanized Bangla, and Romanized Chakma. Our dataset is created by augmenting the MELD corpus with LLM-generated romanizations that are rigorously validated by native speakers. We establish robust machine translation baselines across six diverse language and script pairs. Our experiments reveal that a multilingual training approach, combining English and Bangla as source languages, yields a dramatic performance increase, achieving a BLEU score of 0.5228 for Chakma translation, a 124% relative improvement over the best bilingual model. We release ChakmaBridge to facilitate research in low-resource MT and aid in the digital preservation of this endangered language.</abstract>
<identifier type="citekey">rahman-etal-2025-chakmabridge</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.21/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>259</start>
<end>265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChakmaBridge: A Five-Way Parallel Corpus for Navigating the Script Divide in an Endangered Language
%A Rahman, Md. Abdur
%A Bhuiyan, Md. Tofael Ahmed
%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 rahman-etal-2025-chakmabridge
%X The advancement of NLP technologies for low-resource and endangered languages is critically hindered by the scarcity of high-quality, parallel corpora. This is particularly true for languages like Chakma, which also faces the challenge of prevalent non-standard, romanized script usage in digital communication. To address this, we introduce ChakmaBridge, the first five-way parallel corpus for Chakma, containing 807 sentences aligned across English, Standard Bangla, Bengali-script Chakma, Romanized Bangla, and Romanized Chakma. Our dataset is created by augmenting the MELD corpus with LLM-generated romanizations that are rigorously validated by native speakers. We establish robust machine translation baselines across six diverse language and script pairs. Our experiments reveal that a multilingual training approach, combining English and Bangla as source languages, yields a dramatic performance increase, achieving a BLEU score of 0.5228 for Chakma translation, a 124% relative improvement over the best bilingual model. We release ChakmaBridge to facilitate research in low-resource MT and aid in the digital preservation of this endangered language.
%U https://aclanthology.org/2025.banglalp-1.21/
%P 259-265
Markdown (Informal)
[ChakmaBridge: A Five-Way Parallel Corpus for Navigating the Script Divide in an Endangered Language](https://aclanthology.org/2025.banglalp-1.21/) (Rahman et al., BanglaLP 2025)
ACL