<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajcoomar-2025-kozkreolmru">
    <titleInfo>
        <title>KozKreolMRU WMT 2025 CreoleMT System Description: Koz Kreol: Multi-Stage Training for English–Mauritian Creole MT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yush</namePart>
        <namePart type="family">Rajcoomar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-341-8</identifier>
    </relatedItem>
    <abstract>Mauritian Creole (Kreol Morisyen), spoken by approximately 1.5 million people worldwide, faces significant challenges in digital language technology due to limited computational resources. This paper presents “Koz Kreol”, a comprehensive approach to English–Mauritian Creole machine translation using a three-stage training methodology: monolingual pretraining, parallel data training, and LoRA fine-tuning. We achieve state-of-the-art results with a 28.82 BLEU score for EN→MFE translation, representing a 74% improvement over ChatGPT-4o. Our work addresses critical data scarcity through the use of existing datasets, synthetic data generation, and community-sourced translations. The methodology provides a replicable framework for other low-resource Creole languages while supporting digital inclusion and cultural preservation for the Mauritian community. This paper consists of both a systems and data subtask submission as part of a Creole MT Shared Task.</abstract>
    <identifier type="citekey">rajcoomar-2025-kozkreolmru</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.92/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>1183</start>
            <end>1190</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T KozKreolMRU WMT 2025 CreoleMT System Description: Koz Kreol: Multi-Stage Training for English–Mauritian Creole MT
%A Rajcoomar, Yush
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F rajcoomar-2025-kozkreolmru
%X Mauritian Creole (Kreol Morisyen), spoken by approximately 1.5 million people worldwide, faces significant challenges in digital language technology due to limited computational resources. This paper presents “Koz Kreol”, a comprehensive approach to English–Mauritian Creole machine translation using a three-stage training methodology: monolingual pretraining, parallel data training, and LoRA fine-tuning. We achieve state-of-the-art results with a 28.82 BLEU score for EN→MFE translation, representing a 74% improvement over ChatGPT-4o. Our work addresses critical data scarcity through the use of existing datasets, synthetic data generation, and community-sourced translations. The methodology provides a replicable framework for other low-resource Creole languages while supporting digital inclusion and cultural preservation for the Mauritian community. This paper consists of both a systems and data subtask submission as part of a Creole MT Shared Task.
%U https://aclanthology.org/2025.wmt-1.92/
%P 1183-1190

Markdown (Informal)

[KozKreolMRU WMT 2025 CreoleMT System Description: Koz Kreol: Multi-Stage Training for English–Mauritian Creole MT](https://aclanthology.org/2025.wmt-1.92/) (Rajcoomar, WMT 2025)

• KozKreolMRU WMT 2025 CreoleMT System Description: Koz Kreol: Multi-Stage Training for English–Mauritian Creole MT (Rajcoomar, WMT 2025)

ACL

• Yush Rajcoomar. 2025. KozKreolMRU WMT 2025 CreoleMT System Description: Koz Kreol: Multi-Stage Training for English–Mauritian Creole MT. In Proceedings of the Tenth Conference on Machine Translation, pages 1183–1190, Suzhou, China. Association for Computational Linguistics.