@inproceedings{robinson-2025-jhu,
title = "{JHU} {WMT} 2025 {C}reole{MT} System Description: Data for Belizean {K}riol and {F}rench Guianese Creole {MT}",
author = "Robinson, Nathaniel",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Tenth Conference on Machine Translation",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wmt-1.93/",
pages = "1191--1197",
ISBN = "979-8-89176-341-8",
abstract = "This document details the Johns Hopkins University{'}s submission to the 2025 WMT Shared Task for Creole Language Translation. We submitted exclusively to the data subtask, contributing machine translation bitext corpora for Belizean Kriol with English translations, and French Guianese Creole with French translations. These datasets contain 5,530 and 1,671 parallel lines of text, respectively, thus amounting to an 2,300{\%} increase in publicly available lines of bitext for Belizean Creole with English, and an 370{\%} such increase for French Guianese Creole with French. Experiments demonstrate genre-dependent improvements on our proposed test sets when the relevant state-of-the-art model is fine-tuned on our proposed train sets, with improvements across genres of up to 33.3 chrF++."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="robinson-2025-jhu">
<titleInfo>
<title>JHU WMT 2025 CreoleMT System Description: Data for Belizean Kriol and French Guianese Creole MT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Robinson</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>This document details the Johns Hopkins University’s submission to the 2025 WMT Shared Task for Creole Language Translation. We submitted exclusively to the data subtask, contributing machine translation bitext corpora for Belizean Kriol with English translations, and French Guianese Creole with French translations. These datasets contain 5,530 and 1,671 parallel lines of text, respectively, thus amounting to an 2,300% increase in publicly available lines of bitext for Belizean Creole with English, and an 370% such increase for French Guianese Creole with French. Experiments demonstrate genre-dependent improvements on our proposed test sets when the relevant state-of-the-art model is fine-tuned on our proposed train sets, with improvements across genres of up to 33.3 chrF++.</abstract>
<identifier type="citekey">robinson-2025-jhu</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.93/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1191</start>
<end>1197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JHU WMT 2025 CreoleMT System Description: Data for Belizean Kriol and French Guianese Creole MT
%A Robinson, Nathaniel
%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 robinson-2025-jhu
%X This document details the Johns Hopkins University’s submission to the 2025 WMT Shared Task for Creole Language Translation. We submitted exclusively to the data subtask, contributing machine translation bitext corpora for Belizean Kriol with English translations, and French Guianese Creole with French translations. These datasets contain 5,530 and 1,671 parallel lines of text, respectively, thus amounting to an 2,300% increase in publicly available lines of bitext for Belizean Creole with English, and an 370% such increase for French Guianese Creole with French. Experiments demonstrate genre-dependent improvements on our proposed test sets when the relevant state-of-the-art model is fine-tuned on our proposed train sets, with improvements across genres of up to 33.3 chrF++.
%U https://aclanthology.org/2025.wmt-1.93/
%P 1191-1197
Markdown (Informal)
[JHU WMT 2025 CreoleMT System Description: Data for Belizean Kriol and French Guianese Creole MT](https://aclanthology.org/2025.wmt-1.93/) (Robinson, WMT 2025)
ACL