@inproceedings{chakma-etal-2026-chakmanmt,
title = "{C}hakma{NMT}: Machine Translation for a Low-Resource and Endangered Language via Transliteration",
author = "Chakma, Aunabil and
Chakma, Aditya and
Hasan, Masum and
Khisa, Soham and
Tripura, Chumui and
Shahriyar, Rifat",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.5/",
pages = "64--81",
ISBN = "979-8-89176-474-3",
abstract = "We present a systematic study of machine translation for Chakma, an endangered and extremely low-resource Indo-Aryan language. We introduce a large Chakma{--}Bangla machine translation resource comprising 15,021 parallel translation pairs, 42,783 Chakma monolingual sentences, and a trilingual evaluation benchmark. To address data scarcity and the script mismatch between Chakma and Bangla, we develop a character-level transliteration framework that enables transfer from Bangla and multilingual pretrained models. We evaluate from-scratch machine translation systems, fine-tuned pretrained models, and large language models using in-context learning. Our results show that transliteration is crucial for the tested pretrained models and that performance is strongly direction-dependent: in-context learning performs best for Chakma-to-Bangla translation, while Bangla-to-Chakma remains considerably more challenging, with the strongest approach depending on the evaluation metric."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakma-etal-2026-chakmanmt">
<titleInfo>
<title>ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aunabil</namePart>
<namePart type="family">Chakma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Chakma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masum</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soham</namePart>
<namePart type="family">Khisa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chumui</namePart>
<namePart type="family">Tripura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rifat</namePart>
<namePart type="family">Shahriyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>We present a systematic study of machine translation for Chakma, an endangered and extremely low-resource Indo-Aryan language. We introduce a large Chakma–Bangla machine translation resource comprising 15,021 parallel translation pairs, 42,783 Chakma monolingual sentences, and a trilingual evaluation benchmark. To address data scarcity and the script mismatch between Chakma and Bangla, we develop a character-level transliteration framework that enables transfer from Bangla and multilingual pretrained models. We evaluate from-scratch machine translation systems, fine-tuned pretrained models, and large language models using in-context learning. Our results show that transliteration is crucial for the tested pretrained models and that performance is strongly direction-dependent: in-context learning performs best for Chakma-to-Bangla translation, while Bangla-to-Chakma remains considerably more challenging, with the strongest approach depending on the evaluation metric.</abstract>
<identifier type="citekey">chakma-etal-2026-chakmanmt</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.5/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>64</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration
%A Chakma, Aunabil
%A Chakma, Aditya
%A Hasan, Masum
%A Khisa, Soham
%A Tripura, Chumui
%A Shahriyar, Rifat
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F chakma-etal-2026-chakmanmt
%X We present a systematic study of machine translation for Chakma, an endangered and extremely low-resource Indo-Aryan language. We introduce a large Chakma–Bangla machine translation resource comprising 15,021 parallel translation pairs, 42,783 Chakma monolingual sentences, and a trilingual evaluation benchmark. To address data scarcity and the script mismatch between Chakma and Bangla, we develop a character-level transliteration framework that enables transfer from Bangla and multilingual pretrained models. We evaluate from-scratch machine translation systems, fine-tuned pretrained models, and large language models using in-context learning. Our results show that transliteration is crucial for the tested pretrained models and that performance is strongly direction-dependent: in-context learning performs best for Chakma-to-Bangla translation, while Bangla-to-Chakma remains considerably more challenging, with the strongest approach depending on the evaluation metric.
%U https://aclanthology.org/2026.wmt-main.5/
%P 64-81
Markdown (Informal)
[ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration](https://aclanthology.org/2026.wmt-main.5/) (Chakma et al., WMT 2026)
ACL