Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

Evelyn Garland; Carola Berger

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

In this paper, we present 1020 Group’s submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low-cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.

Anthology ID:: 2026.wmt-main.96
Volume:: Proceedings of the Eleventh Conference on Machine Translation
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venues:: WMT | WS
SIG:: SIGMT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1638–1643
Language:
URL:: https://aclanthology.org/2026.wmt-main.96/
DOI:
Bibkey:
Cite (ACL):: Evelyn Garland and Carola Berger. 2026. Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation. In Proceedings of the Eleventh Conference on Machine Translation, pages 1638–1643, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation (Garland & Berger, WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.96.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{garland-berger-2026-pterodactyl,
    title = "Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation",
    author = "Garland, Evelyn  and
      Berger, Carola",
    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.96/",
    pages = "1638--1643",
    ISBN = "979-8-89176-474-3",
    abstract = "In this paper, we present 1020 Group{'}s submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low-cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garland-berger-2026-pterodactyl">
    <titleInfo>
        <title>Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Evelyn</namePart>
        <namePart type="family">Garland</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carola</namePart>
        <namePart type="family">Berger</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>In this paper, we present 1020 Group’s submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low-cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.</abstract>
    <identifier type="citekey">garland-berger-2026-pterodactyl</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.96/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1638</start>
            <end>1643</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
%A Garland, Evelyn
%A Berger, Carola
%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 garland-berger-2026-pterodactyl
%X In this paper, we present 1020 Group’s submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low-cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.
%U https://aclanthology.org/2026.wmt-main.96/
%P 1638-1643

Download as File

Markdown (Informal)

[Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation](https://aclanthology.org/2026.wmt-main.96/) (Garland & Berger, WMT 2026)

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation (Garland & Berger, WMT 2026)

ACL

Evelyn Garland and Carola Berger. 2026. Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation. In Proceedings of the Eleventh Conference on Machine Translation, pages 1638–1643, Budapest, Hungary. Association for Computational Linguistics.