Long-context Reference-based MT Quality Estimation

Sami Haq; Chinonso Osuji; Sheila Castilho; Brian Davis; Thiago Castro Ferreira

Long-context Reference-based MT Quality Estimation

Sami Haq, Chinonso Osuji, Sheila Castilho, Brian Davis, Thiago Castro Ferreira

Correct Metadata for

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>.

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 our submission to the Tenth Conference on Machine Translation (WMT25) Shared Task on Automated Translation Quality Evaluation. Our systems are built upon the COMET framework and trained to predict segment-level ESA scores using augmented long-context data. To construct long-context training examples, we concatenate multiple in-domain sentences and compute a weighted average of their scores. We further integrate human judgment datasets MQM, SQM, and DA) through score normalisation and train multilingual models on the source, hypothesis, and reference translations. Experimental results demonstrate that incorporating long-context information yields higher correlations with human judgments compared to models trained exclusively on short segments.

Anthology ID:: 2025.wmt-1.64
Volume:: Proceedings of the Tenth Conference on Machine Translation
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:: WMT
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 905–912
Language:
URL:: https://aclanthology.org/2025.wmt-1.64/
DOI:
Bibkey:
Cite (ACL):: Sami Haq, Chinonso Osuji, Sheila Castilho, Brian Davis, and Thiago Castro Ferreira. 2025. Long-context Reference-based MT Quality Estimation. In Proceedings of the Tenth Conference on Machine Translation, pages 905–912, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: Long-context Reference-based MT Quality Estimation (Haq et al., WMT 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.wmt-1.64.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{haq-etal-2025-long,
    title = "Long-context Reference-based {MT} Quality Estimation",
    author = "Haq, Sami  and
      Osuji, Chinonso  and
      Castilho, Sheila  and
      Davis, Brian  and
      Castro Ferreira, Thiago",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Tenth Conference on Machine Translation",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.wmt-1.64/",
    pages = "905--912",
    ISBN = "979-8-89176-341-8",
    abstract = "In this paper, we present our submission to the Tenth Conference on Machine Translation (WMT25) Shared Task on Automated Translation Quality Evaluation. Our systems are built upon the COMET framework and trained to predict segment-level ESA scores using augmented long-context data. To construct long-context training examples, we concatenate multiple in-domain sentences and compute a weighted average of their scores. We further integrate human judgment datasets MQM, SQM, and DA) through score normalisation and train multilingual models on the source, hypothesis, and reference translations. Experimental results demonstrate that incorporating long-context information yields higher correlations with human judgments compared to models trained exclusively on short segments."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haq-etal-2025-long">
    <titleInfo>
        <title>Long-context Reference-based MT Quality Estimation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sami</namePart>
        <namePart type="family">Haq</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chinonso</namePart>
        <namePart type="family">Osuji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sheila</namePart>
        <namePart type="family">Castilho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Brian</namePart>
        <namePart type="family">Davis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thiago</namePart>
        <namePart type="family">Castro Ferreira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-341-8</identifier>
    </relatedItem>
    <abstract>In this paper, we present our submission to the Tenth Conference on Machine Translation (WMT25) Shared Task on Automated Translation Quality Evaluation. Our systems are built upon the COMET framework and trained to predict segment-level ESA scores using augmented long-context data. To construct long-context training examples, we concatenate multiple in-domain sentences and compute a weighted average of their scores. We further integrate human judgment datasets MQM, SQM, and DA) through score normalisation and train multilingual models on the source, hypothesis, and reference translations. Experimental results demonstrate that incorporating long-context information yields higher correlations with human judgments compared to models trained exclusively on short segments.</abstract>
    <identifier type="citekey">haq-etal-2025-long</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.64/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>905</start>
            <end>912</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Long-context Reference-based MT Quality Estimation
%A Haq, Sami
%A Osuji, Chinonso
%A Castilho, Sheila
%A Davis, Brian
%A Castro Ferreira, Thiago
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F haq-etal-2025-long
%X In this paper, we present our submission to the Tenth Conference on Machine Translation (WMT25) Shared Task on Automated Translation Quality Evaluation. Our systems are built upon the COMET framework and trained to predict segment-level ESA scores using augmented long-context data. To construct long-context training examples, we concatenate multiple in-domain sentences and compute a weighted average of their scores. We further integrate human judgment datasets MQM, SQM, and DA) through score normalisation and train multilingual models on the source, hypothesis, and reference translations. Experimental results demonstrate that incorporating long-context information yields higher correlations with human judgments compared to models trained exclusively on short segments.
%U https://aclanthology.org/2025.wmt-1.64/
%P 905-912

Download as File

Markdown (Informal)

[Long-context Reference-based MT Quality Estimation](https://aclanthology.org/2025.wmt-1.64/) (Haq et al., WMT 2025)

Long-context Reference-based MT Quality Estimation (Haq et al., WMT 2025)

ACL

Sami Haq, Chinonso Osuji, Sheila Castilho, Brian Davis, and Thiago Castro Ferreira. 2025. Long-context Reference-based MT Quality Estimation. In Proceedings of the Tenth Conference on Machine Translation, pages 905–912, Suzhou, China. Association for Computational Linguistics.