How many raters do we need to recognize a bad translation via perplexity?

Antonín Otmar; Ondřej Bojar

How many raters do we need to recognize a bad translation via perplexity?

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 evaluated candidate translation pairs with various kinds of damage using perplexity assigned to them by LLMs to see how it holds up as a fluency and adequacy metric. We also explored how the discriminating power of perplexity can be improved by ensembling.

Anthology ID:: 2026.wmt-main.29
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:: 530–540
Language:
URL:: https://aclanthology.org/2026.wmt-main.29/
DOI:
Bibkey:
Cite (ACL):: Antonín Otmar and Ondřej Bojar. 2026. How many raters do we need to recognize a bad translation via perplexity?. In Proceedings of the Eleventh Conference on Machine Translation, pages 530–540, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: How many raters do we need to recognize a bad translation via perplexity? (Otmar & Bojar, WMT 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.wmt-main.29.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{otmar-bojar-2026-many,
    title = "How many raters do we need to recognize a bad translation via perplexity?",
    author = "Otmar, Anton{\'i}n  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.29/",
    pages = "530--540",
    ISBN = "979-8-89176-474-3",
    abstract = "We evaluated candidate translation pairs with various kinds of damage using perplexity assigned to them by LLMs to see how it holds up as a fluency and adequacy metric. We also explored how the discriminating power of perplexity can be improved by ensembling."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otmar-bojar-2026-many">
    <titleInfo>
        <title>How many raters do we need to recognize a bad translation via perplexity?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Antonín</namePart>
        <namePart type="family">Otmar</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 evaluated candidate translation pairs with various kinds of damage using perplexity assigned to them by LLMs to see how it holds up as a fluency and adequacy metric. We also explored how the discriminating power of perplexity can be improved by ensembling.</abstract>
    <identifier type="citekey">otmar-bojar-2026-many</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.29/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>530</start>
            <end>540</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T How many raters do we need to recognize a bad translation via perplexity?
%A Otmar, Antonín
%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 otmar-bojar-2026-many
%X We evaluated candidate translation pairs with various kinds of damage using perplexity assigned to them by LLMs to see how it holds up as a fluency and adequacy metric. We also explored how the discriminating power of perplexity can be improved by ensembling.
%U https://aclanthology.org/2026.wmt-main.29/
%P 530-540

Download as File

Markdown (Informal)

[How many raters do we need to recognize a bad translation via perplexity?](https://aclanthology.org/2026.wmt-main.29/) (Otmar & Bojar, WMT 2026)

How many raters do we need to recognize a bad translation via perplexity? (Otmar & Bojar, WMT 2026)

ACL

Antonín Otmar and Ondřej Bojar. 2026. How many raters do we need to recognize a bad translation via perplexity?. In Proceedings of the Eleventh Conference on Machine Translation, pages 530–540, Budapest, Hungary. Association for Computational Linguistics.