@inproceedings{boudraa-2026-magadir,
title = "{MAGADIR} at {WMT} 2026: Cross-System {QE} Re-ranking and Entity-Aware Selection for Low-Resource {A}rabic-{E}nglish Translation",
author = "Boudraa, Hossam",
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.169/",
pages = "2280--2297",
ISBN = "979-8-89176-474-3",
abstract = "We present MAGADIR{'}s submissions to the WMT 2026 Low-Resource Arabic{--}Asian Language Translation Shared Task for English{--}Arabic translation. Our systems combine a small official parallel corpus, parameter-efficient adaptation of open-weight multilingual models, and segment-level, reference-free quality-estimation re-ranking over heterogeneous cross-system candidate pools. For Arabic-to-English translation, the pool includes supervised LoRA-adapted NLLB and Hunyuan-family models alongside zero-shot Hunyuan/HY-MT and Gemma models. For English-to-Arabic, we select among zero-shot Hunyuan/HY-MT, Gemma, Aya, and NLLB candidates. The Arabic-to-English primary system uses MetricX-24-QE together with a Wikidata-derived entity-recall floor that vetoes candidates omitting recognized proper names before quality estimation determines the final output; the English-to-Arabic primary uses COMETKiwi without an entity constraint. On the official Challenge Test, the Arabic-to-English primary achieves 27.45 BLEU, 56.61 chrF, and 81.94 COMET, while the English-to-Arabic primary obtains 14.59 BLEU, 51.48 chrF, and 83.88 COMET. Relative to our own single-model contrastives, QE-guided cross-system selection improves COMET by up to 1.94 points for Arabic-to-English and 0.81 points for English-to-Arabic, although some contrastive systems retain stronger lexical-overlap scores. This exposes a persistent trade-off between neural adequacy objectives and reference-based surface metrics. A post-hoc matched control separates the Arabic-to-English entity floor from the otherwise confounded change in QE utility. The floor accounts for 83{\%} of the entity-recall gain while changing only 7{\%} of outputs and imposing effectively no COMETKiwi cost (+0.0002); the switch from COMETKiwi to MetricX rewrites 74{\%} of outputs and accounts for the full {\ensuremath{-}}0.0085 COMETKiwi difference. Our audit also identifies an important limitation: on approximately 65{\%} of entity-bearing segments, no candidate preserves every recognized entity in canonical form, leaving the veto with no feasible alternative. These findings motivate routine reference-free entity auditing, more diverse candidate pools, expanded gazetteer coverage, and transliteration-aware entity matching for QE-selected translation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boudraa-2026-magadir">
<titleInfo>
<title>MAGADIR at WMT 2026: Cross-System QE Re-ranking and Entity-Aware Selection for Low-Resource Arabic-English Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hossam</namePart>
<namePart type="family">Boudraa</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 MAGADIR’s submissions to the WMT 2026 Low-Resource Arabic–Asian Language Translation Shared Task for English–Arabic translation. Our systems combine a small official parallel corpus, parameter-efficient adaptation of open-weight multilingual models, and segment-level, reference-free quality-estimation re-ranking over heterogeneous cross-system candidate pools. For Arabic-to-English translation, the pool includes supervised LoRA-adapted NLLB and Hunyuan-family models alongside zero-shot Hunyuan/HY-MT and Gemma models. For English-to-Arabic, we select among zero-shot Hunyuan/HY-MT, Gemma, Aya, and NLLB candidates. The Arabic-to-English primary system uses MetricX-24-QE together with a Wikidata-derived entity-recall floor that vetoes candidates omitting recognized proper names before quality estimation determines the final output; the English-to-Arabic primary uses COMETKiwi without an entity constraint. On the official Challenge Test, the Arabic-to-English primary achieves 27.45 BLEU, 56.61 chrF, and 81.94 COMET, while the English-to-Arabic primary obtains 14.59 BLEU, 51.48 chrF, and 83.88 COMET. Relative to our own single-model contrastives, QE-guided cross-system selection improves COMET by up to 1.94 points for Arabic-to-English and 0.81 points for English-to-Arabic, although some contrastive systems retain stronger lexical-overlap scores. This exposes a persistent trade-off between neural adequacy objectives and reference-based surface metrics. A post-hoc matched control separates the Arabic-to-English entity floor from the otherwise confounded change in QE utility. The floor accounts for 83% of the entity-recall gain while changing only 7% of outputs and imposing effectively no COMETKiwi cost (+0.0002); the switch from COMETKiwi to MetricX rewrites 74% of outputs and accounts for the full \ensuremath-0.0085 COMETKiwi difference. Our audit also identifies an important limitation: on approximately 65% of entity-bearing segments, no candidate preserves every recognized entity in canonical form, leaving the veto with no feasible alternative. These findings motivate routine reference-free entity auditing, more diverse candidate pools, expanded gazetteer coverage, and transliteration-aware entity matching for QE-selected translation systems.</abstract>
<identifier type="citekey">boudraa-2026-magadir</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.169/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2280</start>
<end>2297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAGADIR at WMT 2026: Cross-System QE Re-ranking and Entity-Aware Selection for Low-Resource Arabic-English Translation
%A Boudraa, Hossam
%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 boudraa-2026-magadir
%X We present MAGADIR’s submissions to the WMT 2026 Low-Resource Arabic–Asian Language Translation Shared Task for English–Arabic translation. Our systems combine a small official parallel corpus, parameter-efficient adaptation of open-weight multilingual models, and segment-level, reference-free quality-estimation re-ranking over heterogeneous cross-system candidate pools. For Arabic-to-English translation, the pool includes supervised LoRA-adapted NLLB and Hunyuan-family models alongside zero-shot Hunyuan/HY-MT and Gemma models. For English-to-Arabic, we select among zero-shot Hunyuan/HY-MT, Gemma, Aya, and NLLB candidates. The Arabic-to-English primary system uses MetricX-24-QE together with a Wikidata-derived entity-recall floor that vetoes candidates omitting recognized proper names before quality estimation determines the final output; the English-to-Arabic primary uses COMETKiwi without an entity constraint. On the official Challenge Test, the Arabic-to-English primary achieves 27.45 BLEU, 56.61 chrF, and 81.94 COMET, while the English-to-Arabic primary obtains 14.59 BLEU, 51.48 chrF, and 83.88 COMET. Relative to our own single-model contrastives, QE-guided cross-system selection improves COMET by up to 1.94 points for Arabic-to-English and 0.81 points for English-to-Arabic, although some contrastive systems retain stronger lexical-overlap scores. This exposes a persistent trade-off between neural adequacy objectives and reference-based surface metrics. A post-hoc matched control separates the Arabic-to-English entity floor from the otherwise confounded change in QE utility. The floor accounts for 83% of the entity-recall gain while changing only 7% of outputs and imposing effectively no COMETKiwi cost (+0.0002); the switch from COMETKiwi to MetricX rewrites 74% of outputs and accounts for the full \ensuremath-0.0085 COMETKiwi difference. Our audit also identifies an important limitation: on approximately 65% of entity-bearing segments, no candidate preserves every recognized entity in canonical form, leaving the veto with no feasible alternative. These findings motivate routine reference-free entity auditing, more diverse candidate pools, expanded gazetteer coverage, and transliteration-aware entity matching for QE-selected translation systems.
%U https://aclanthology.org/2026.wmt-main.169/
%P 2280-2297
Markdown (Informal)
[MAGADIR at WMT 2026: Cross-System QE Re-ranking and Entity-Aware Selection for Low-Resource Arabic-English Translation](https://aclanthology.org/2026.wmt-main.169/) (Boudraa, WMT 2026)
ACL