Dubformer at WMT26 General MT: Translating the Video, Not the Transcript

Sergey Dukanov; Maria Tsyurupa; Anton Dvorkovich

Dubformer at WMT26 General MT: Translating the Video, Not the Transcript

Sergey Dukanov, Maria Tsyurupa, Anton Dvorkovich

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 system Dubformer entered in the WMT26 General MT shared task, an un- constrained system built on our video-dubbing pipeline. It rests on two commitments. A doc- ument is never translated as raw text: it is first decomposed into a structure chosen for its do- main — scenes carrying speaker and audio- visual context for spoken dialogue, markup- masked segments for web documents, value- only segments for localization resources — so that non-linguistic material is protected by construction and everything needed for consis- tency is in front of the model at once. And no translation is taken on trust: every segment is checked by a second model from a different family for hallucination and for drift from the meaning of the source, and a segment it rejects is re-translated with the reason attached rather than filled in from a fallback.

Anthology ID:: 2026.wmt-main.63
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:: 1231–1234
Language:
URL:: https://aclanthology.org/2026.wmt-main.63/
DOI:
Bibkey:
Cite (ACL):: Sergey Dukanov, Maria Tsyurupa, and Anton Dvorkovich. 2026. Dubformer at WMT26 General MT: Translating the Video, Not the Transcript. In Proceedings of the Eleventh Conference on Machine Translation, pages 1231–1234, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Dubformer at WMT26 General MT: Translating the Video, Not the Transcript (Dukanov et al., WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.63.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{dukanov-etal-2026-dubformer,
    title = "Dubformer at {WMT}26 General {MT}: Translating the Video, Not the Transcript",
    author = "Dukanov, Sergey  and
      Tsyurupa, Maria  and
      Dvorkovich, Anton",
    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.63/",
    pages = "1231--1234",
    ISBN = "979-8-89176-474-3",
    abstract = "We describe the system Dubformer entered in the WMT26 General MT shared task, an un- constrained system built on our video-dubbing pipeline. It rests on two commitments. A doc- ument is never translated as raw text: it is first decomposed into a structure chosen for its do- main {---} scenes carrying speaker and audio- visual context for spoken dialogue, markup- masked segments for web documents, value- only segments for localization resources {---} so that non-linguistic material is protected by construction and everything needed for consis- tency is in front of the model at once. And no translation is taken on trust: every segment is checked by a second model from a different family for hallucination and for drift from the meaning of the source, and a segment it rejects is re-translated with the reason attached rather than filled in from a fallback."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dukanov-etal-2026-dubformer">
    <titleInfo>
        <title>Dubformer at WMT26 General MT: Translating the Video, Not the Transcript</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sergey</namePart>
        <namePart type="family">Dukanov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Tsyurupa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anton</namePart>
        <namePart type="family">Dvorkovich</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 system Dubformer entered in the WMT26 General MT shared task, an un- constrained system built on our video-dubbing pipeline. It rests on two commitments. A doc- ument is never translated as raw text: it is first decomposed into a structure chosen for its do- main — scenes carrying speaker and audio- visual context for spoken dialogue, markup- masked segments for web documents, value- only segments for localization resources — so that non-linguistic material is protected by construction and everything needed for consis- tency is in front of the model at once. And no translation is taken on trust: every segment is checked by a second model from a different family for hallucination and for drift from the meaning of the source, and a segment it rejects is re-translated with the reason attached rather than filled in from a fallback.</abstract>
    <identifier type="citekey">dukanov-etal-2026-dubformer</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.63/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1231</start>
            <end>1234</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Dubformer at WMT26 General MT: Translating the Video, Not the Transcript
%A Dukanov, Sergey
%A Tsyurupa, Maria
%A Dvorkovich, Anton
%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 dukanov-etal-2026-dubformer
%X We describe the system Dubformer entered in the WMT26 General MT shared task, an un- constrained system built on our video-dubbing pipeline. It rests on two commitments. A doc- ument is never translated as raw text: it is first decomposed into a structure chosen for its do- main — scenes carrying speaker and audio- visual context for spoken dialogue, markup- masked segments for web documents, value- only segments for localization resources — so that non-linguistic material is protected by construction and everything needed for consis- tency is in front of the model at once. And no translation is taken on trust: every segment is checked by a second model from a different family for hallucination and for drift from the meaning of the source, and a segment it rejects is re-translated with the reason attached rather than filled in from a fallback.
%U https://aclanthology.org/2026.wmt-main.63/
%P 1231-1234

Download as File

Markdown (Informal)

[Dubformer at WMT26 General MT: Translating the Video, Not the Transcript](https://aclanthology.org/2026.wmt-main.63/) (Dukanov et al., WMT 2026)

Dubformer at WMT26 General MT: Translating the Video, Not the Transcript (Dukanov et al., WMT 2026)

ACL

Sergey Dukanov, Maria Tsyurupa, and Anton Dvorkovich. 2026. Dubformer at WMT26 General MT: Translating the Video, Not the Transcript. In Proceedings of the Eleventh Conference on Machine Translation, pages 1231–1234, Budapest, Hungary. Association for Computational Linguistics.