@inproceedings{oztop-2026-kyx,
title = "{KYX} {WMT} 2026 {C}reole{MT} System Description: A Contamination- and Orthography-Aware Evaluation for {R}{\'e}union Creole to {E}nglish",
author = {{\"O}ztop, Yusuf},
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.190/",
pages = "2463--2470",
ISBN = "979-8-89176-474-3",
abstract = "This paper presents the KYX submission to the WMT 2026 CreoleMT shared task for R{\'e}union Creole to English (rcf-eng). It is mostly about how such a system should be evaluated. The pair is an extreme case: 191 training pairs, a 34-sentence development set, and no standard orthography. On a benchmark this small, a single chrF++ score is easy to over-read, so we pair our system with a contamination- and orthography-aware evaluation. The system continue-trains the official baseline adapter with QLoRA and raises the raw dev score by +13.3 chrF++. But a near-duplicate audit finds that six of the 34 dev sources are paraphrases of training sentences, which the exact-match check WMT26 mandates reports as 0{\%} overlap. After decontamination the gain is +10.0. Our official test score then comes in 0.8 chrF++ below the decontaminated estimate and 5.1 below the raw one, but our margin over the baseline falls to +3.9, so even the adjusted gain was optimistic. A data-scaling ablation traces the gain to the provided real pairs, not to synthetic data. A source-spelling stress test then shows the advantage shrinks when the input is re-spelled into equally valid variants, though at this sample size the effect is not stable. We conclude that exact-match contamination checks are not enough on tiny benchmarks, and that scores like ours should be read with care. The same caution applies to any low-resource pair with only a few dozen dev sentences. We release the system, the audit, and all data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oztop-2026-kyx">
<titleInfo>
<title>KYX WMT 2026 CreoleMT System Description: A Contamination- and Orthography-Aware Evaluation for Réunion Creole to English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yusuf</namePart>
<namePart type="family">Öztop</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>This paper presents the KYX submission to the WMT 2026 CreoleMT shared task for Réunion Creole to English (rcf-eng). It is mostly about how such a system should be evaluated. The pair is an extreme case: 191 training pairs, a 34-sentence development set, and no standard orthography. On a benchmark this small, a single chrF++ score is easy to over-read, so we pair our system with a contamination- and orthography-aware evaluation. The system continue-trains the official baseline adapter with QLoRA and raises the raw dev score by +13.3 chrF++. But a near-duplicate audit finds that six of the 34 dev sources are paraphrases of training sentences, which the exact-match check WMT26 mandates reports as 0% overlap. After decontamination the gain is +10.0. Our official test score then comes in 0.8 chrF++ below the decontaminated estimate and 5.1 below the raw one, but our margin over the baseline falls to +3.9, so even the adjusted gain was optimistic. A data-scaling ablation traces the gain to the provided real pairs, not to synthetic data. A source-spelling stress test then shows the advantage shrinks when the input is re-spelled into equally valid variants, though at this sample size the effect is not stable. We conclude that exact-match contamination checks are not enough on tiny benchmarks, and that scores like ours should be read with care. The same caution applies to any low-resource pair with only a few dozen dev sentences. We release the system, the audit, and all data.</abstract>
<identifier type="citekey">oztop-2026-kyx</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.190/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2463</start>
<end>2470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KYX WMT 2026 CreoleMT System Description: A Contamination- and Orthography-Aware Evaluation for Réunion Creole to English
%A Öztop, Yusuf
%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 oztop-2026-kyx
%X This paper presents the KYX submission to the WMT 2026 CreoleMT shared task for Réunion Creole to English (rcf-eng). It is mostly about how such a system should be evaluated. The pair is an extreme case: 191 training pairs, a 34-sentence development set, and no standard orthography. On a benchmark this small, a single chrF++ score is easy to over-read, so we pair our system with a contamination- and orthography-aware evaluation. The system continue-trains the official baseline adapter with QLoRA and raises the raw dev score by +13.3 chrF++. But a near-duplicate audit finds that six of the 34 dev sources are paraphrases of training sentences, which the exact-match check WMT26 mandates reports as 0% overlap. After decontamination the gain is +10.0. Our official test score then comes in 0.8 chrF++ below the decontaminated estimate and 5.1 below the raw one, but our margin over the baseline falls to +3.9, so even the adjusted gain was optimistic. A data-scaling ablation traces the gain to the provided real pairs, not to synthetic data. A source-spelling stress test then shows the advantage shrinks when the input is re-spelled into equally valid variants, though at this sample size the effect is not stable. We conclude that exact-match contamination checks are not enough on tiny benchmarks, and that scores like ours should be read with care. The same caution applies to any low-resource pair with only a few dozen dev sentences. We release the system, the audit, and all data.
%U https://aclanthology.org/2026.wmt-main.190/
%P 2463-2470
Markdown (Informal)
[KYX WMT 2026 CreoleMT System Description: A Contamination- and Orthography-Aware Evaluation for Réunion Creole to English](https://aclanthology.org/2026.wmt-main.190/) (Öztop, WMT 2026)
ACL