<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toutou-etal-2026-data">
    <titleInfo>
        <title>Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ammar</namePart>
        <namePart type="family">Toutou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abdelrahman</namePart>
        <namePart type="family">Harb</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christine</namePart>
        <namePart type="family">Basta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sil</namePart>
            <namePart type="family">Hamilton</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="family">Öhman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="given">M</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Hicke</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yuri</namePart>
            <namePart type="family">Bizzoni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Axel</namePart>
            <namePart type="family">Bax</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jacob</namePart>
            <namePart type="given">A</namePart>
            <namePart type="family">Matthews</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mika</namePart>
            <namePart type="family">Hämäläinen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-427-9</identifier>
    </relatedItem>
    <abstract>Ancient and endangered languages pose a unique challenge for NLP: their datasets are inherently scarce, difficult to expand, and built from formulaic corpora—making data-quality issues especially consequential yet rarely audited. Motivated by the need to understand what current NMT can realistically achieve for such languages, we investigate hieroglyphic-to-German translation, where a recent study reported 61.5 BLEU using fine-tuned M2M-100. Our reproduction yields only 37.0 BLEU with the released model. Investigating this gap, we find 32% of test targets appear identically in training (16/50; 50% under 8-gram overlap at 70% threshold). This contamination inflates scores dramatically: contaminated samples achieve up to 83.8 BLEU / 0.924 COMET-22 versus 30.9–39.2 BLEU / 0.622–0.676 COMET-22 on clean samples across five model configurations spanning two architectures. Document-level decontamination reduces contaminated BLEU by only 4.6 points because 8/16 targets persist via other source documents—target-level deduplication is required. We release a decontaminated 34-sample test set and establish corrected baselines (30.9–39.2 BLEU), providing a realistic assessment of NMT capability for this endangered writing system.</abstract>
    <identifier type="citekey">toutou-etal-2026-data</identifier>
    <location>
        <url>https://aclanthology.org/2026.nlp4dh-1.6/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>50</start>
            <end>57</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study
%A Toutou, Ammar
%A Harb, Abdelrahman
%A Basta, Christine
%Y Hamilton, Sil
%Y Öhman, Emily
%Y Hicke, Rebecca M. M.
%Y Bizzoni, Yuri
%Y Bax, Axel
%Y Matthews, Jacob A.
%Y Hämäläinen, Mika
%S Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA
%@ 979-8-89176-427-9
%F toutou-etal-2026-data
%X Ancient and endangered languages pose a unique challenge for NLP: their datasets are inherently scarce, difficult to expand, and built from formulaic corpora—making data-quality issues especially consequential yet rarely audited. Motivated by the need to understand what current NMT can realistically achieve for such languages, we investigate hieroglyphic-to-German translation, where a recent study reported 61.5 BLEU using fine-tuned M2M-100. Our reproduction yields only 37.0 BLEU with the released model. Investigating this gap, we find 32% of test targets appear identically in training (16/50; 50% under 8-gram overlap at 70% threshold). This contamination inflates scores dramatically: contaminated samples achieve up to 83.8 BLEU / 0.924 COMET-22 versus 30.9–39.2 BLEU / 0.622–0.676 COMET-22 on clean samples across five model configurations spanning two architectures. Document-level decontamination reduces contaminated BLEU by only 4.6 points because 8/16 targets persist via other source documents—target-level deduplication is required. We release a decontaminated 34-sample test set and establish corrected baselines (30.9–39.2 BLEU), providing a realistic assessment of NMT capability for this endangered writing system.
%U https://aclanthology.org/2026.nlp4dh-1.6/
%P 50-57

Markdown (Informal)

[Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study](https://aclanthology.org/2026.nlp4dh-1.6/) (Toutou et al., NLP4DH 2026)

• Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study (Toutou et al., NLP4DH 2026)

ACL

• Ammar Toutou, Abdelrahman Harb, and Christine Basta. 2026. Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study. In Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities, pages 50–57, San Diego, USA. Association for Computational Linguistics.