CUNI at the WMT26 Automated MT Evaluation Shared Task

Miroslav Hrabal; Ondřej Bojar

CUNI at the WMT26 Automated MT Evaluation Shared Task

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

We describe the CUNI submissions to the WMT26 Automated MT Evaluation Shared Task. We take part in error-span prediction (Task~1) and segment-level quality score prediction (Task~2). Our systems use a single open-weight Gemma 4 31B instruction-tuned model as a backbone. For Task~1, we decompose error prediction into semantic error detection, self-review, and a separate span-alignment step that maps free-form error descriptions to source and target character spans. We submit two variants of this approach, one additionally predicting MQM-style error categories. For Task~2, we explore two complementary approaches: regression over features extracted from the Task~1 predictions and LLM-based direct assessment on a 0–100 scale.

Anthology ID:: 2026.wmt-main.98
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:: 1652–1657
Language:
URL:: https://aclanthology.org/2026.wmt-main.98/
DOI:
Bibkey:
Cite (ACL):: Miroslav Hrabal and Ondřej Bojar. 2026. CUNI at the WMT26 Automated MT Evaluation Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1652–1657, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: CUNI at the WMT26 Automated MT Evaluation Shared Task (Hrabal & Bojar, WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.98.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{hrabal-bojar-2026-cuni,
    title = "{CUNI} at the {WMT}26 Automated {MT} Evaluation Shared Task",
    author = "Hrabal, Miroslav  and
      Bojar, Ond{\v{r}}ej",
    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.98/",
    pages = "1652--1657",
    ISBN = "979-8-89176-474-3",
    abstract = "We describe the CUNI submissions to the WMT26 Automated MT Evaluation Shared Task. We take part in error-span prediction (Task{\textasciitilde}1) and segment-level quality score prediction (Task{\textasciitilde}2). Our systems use a single open-weight Gemma 4 31B instruction-tuned model as a backbone. For Task{\textasciitilde}1, we decompose error prediction into semantic error detection, self-review, and a separate span-alignment step that maps free-form error descriptions to source and target character spans. We submit two variants of this approach, one additionally predicting MQM-style error categories. For Task{\textasciitilde}2, we explore two complementary approaches: regression over features extracted from the Task{\textasciitilde}1 predictions and LLM-based direct assessment on a 0{--}100 scale."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hrabal-bojar-2026-cuni">
    <titleInfo>
        <title>CUNI at the WMT26 Automated MT Evaluation Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Miroslav</namePart>
        <namePart type="family">Hrabal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Bojar</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 describe the CUNI submissions to the WMT26 Automated MT Evaluation Shared Task. We take part in error-span prediction (Task~1) and segment-level quality score prediction (Task~2). Our systems use a single open-weight Gemma 4 31B instruction-tuned model as a backbone. For Task~1, we decompose error prediction into semantic error detection, self-review, and a separate span-alignment step that maps free-form error descriptions to source and target character spans. We submit two variants of this approach, one additionally predicting MQM-style error categories. For Task~2, we explore two complementary approaches: regression over features extracted from the Task~1 predictions and LLM-based direct assessment on a 0–100 scale.</abstract>
    <identifier type="citekey">hrabal-bojar-2026-cuni</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.98/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1652</start>
            <end>1657</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T CUNI at the WMT26 Automated MT Evaluation Shared Task
%A Hrabal, Miroslav
%A Bojar, Ondřej
%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 hrabal-bojar-2026-cuni
%X We describe the CUNI submissions to the WMT26 Automated MT Evaluation Shared Task. We take part in error-span prediction (Task~1) and segment-level quality score prediction (Task~2). Our systems use a single open-weight Gemma 4 31B instruction-tuned model as a backbone. For Task~1, we decompose error prediction into semantic error detection, self-review, and a separate span-alignment step that maps free-form error descriptions to source and target character spans. We submit two variants of this approach, one additionally predicting MQM-style error categories. For Task~2, we explore two complementary approaches: regression over features extracted from the Task~1 predictions and LLM-based direct assessment on a 0–100 scale.
%U https://aclanthology.org/2026.wmt-main.98/
%P 1652-1657

Download as File

Markdown (Informal)

[CUNI at the WMT26 Automated MT Evaluation Shared Task](https://aclanthology.org/2026.wmt-main.98/) (Hrabal & Bojar, WMT 2026)

CUNI at the WMT26 Automated MT Evaluation Shared Task (Hrabal & Bojar, WMT 2026)

ACL

Miroslav Hrabal and Ondřej Bojar. 2026. CUNI at the WMT26 Automated MT Evaluation Shared Task. In Proceedings of the Eleventh Conference on Machine Translation, pages 1652–1657, Budapest, Hungary. Association for Computational Linguistics.