<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-2025-quality">
    <titleInfo>
        <title>Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Prashant</namePart>
        <namePart type="family">Sharma</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>This paper describes our submission to the WMT25 Automated Translation Quality Evaluation Systems Task 3 - QE-informed Segment-level Error Correction. We propose a two-step approach for Automatic Post-Editing (APE) that leverages natural language explanations of translation errors. Our method first utilises the xTower model to generate a descriptive explanation of the errors present in a machine-translated segment, given the source text, the machine translation, and quality estimation annotations. This explanation is then provided as a prompt to a powerful Large Language Model, Gemini 1.5 Pro, which generates the final, corrected translation. This approach is inspired by recent work in edit-based APE and aims to improve the interpretability and performance of APE systems. We Evaluated across six language pairs (EN→ZH, EN→CS, EN→IS, EN→JA, EN→RU, EN→UK), our approach demonstrates promising results, especially in cases requiring fine-grained edits.</abstract>
    <identifier type="citekey">sharma-2025-quality</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.75/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>999</start>
            <end>1003</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models
%A Sharma, Prashant
%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 sharma-2025-quality
%X This paper describes our submission to the WMT25 Automated Translation Quality Evaluation Systems Task 3 - QE-informed Segment-level Error Correction. We propose a two-step approach for Automatic Post-Editing (APE) that leverages natural language explanations of translation errors. Our method first utilises the xTower model to generate a descriptive explanation of the errors present in a machine-translated segment, given the source text, the machine translation, and quality estimation annotations. This explanation is then provided as a prompt to a powerful Large Language Model, Gemini 1.5 Pro, which generates the final, corrected translation. This approach is inspired by recent work in edit-based APE and aims to improve the interpretability and performance of APE systems. We Evaluated across six language pairs (EN→ZH, EN→CS, EN→IS, EN→JA, EN→RU, EN→UK), our approach demonstrates promising results, especially in cases requiring fine-grained edits.
%U https://aclanthology.org/2025.wmt-1.75/
%P 999-1003

Markdown (Informal)

[Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models](https://aclanthology.org/2025.wmt-1.75/) (Sharma, WMT 2025)

• Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models (Sharma, WMT 2025)

ACL

• Prashant Sharma. 2025. Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models. In Proceedings of the Tenth Conference on Machine Translation, pages 999–1003, Suzhou, China. Association for Computational Linguistics.