<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uramova-etal-2026-imgmt">
    <titleInfo>
        <title>ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Šárka</namePart>
        <namePart type="family">Uramová</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Petar</namePart>
        <namePart type="family">Petrov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">Jon</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>
    <name type="personal">
        <namePart type="given">Michal</namePart>
        <namePart type="family">Novák</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>Text-in-image translation aims to translate all textual content embedded in an image. In Text Image Translation (TIT), the output is translated text; In-Image Machine Translation (IIMT) additionally renders the translation back into the image. We introduce ImgMT, a massively multilingual dataset and benchmark mined from localized SVG illustrations on Wikimedia Commons, focusing on diagrams, maps, and infographics. ImgMT contains 35,612 aligned image pairs grouped into 1,855 image sets, spanning 129 languages, 20+ writing systems, and 4,886 language pairs.\par We propose a multi-level evaluation protocol that measures source-side text-region detection and OCR accuracy alongside target-side translation quality. We benchmark several multimodal large language models and a dedicated TIT system in English-to-X and X-to-English settings, and find that the source language and writing system substantially affect TIT quality. Finally, we show that ImgMT is not well suited for isolating the contribution of visual information in multimodal translation.</abstract>
    <identifier type="citekey">uramova-etal-2026-imgmt</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.43/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>765</start>
            <end>781</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation
%A Uramová, Šárka
%A Petrov, Petar
%A Jon, Josef
%A Bojar, Ondřej
%A Novák, Michal
%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 uramova-etal-2026-imgmt
%X Text-in-image translation aims to translate all textual content embedded in an image. In Text Image Translation (TIT), the output is translated text; In-Image Machine Translation (IIMT) additionally renders the translation back into the image. We introduce ImgMT, a massively multilingual dataset and benchmark mined from localized SVG illustrations on Wikimedia Commons, focusing on diagrams, maps, and infographics. ImgMT contains 35,612 aligned image pairs grouped into 1,855 image sets, spanning 129 languages, 20+ writing systems, and 4,886 language pairs.\par We propose a multi-level evaluation protocol that measures source-side text-region detection and OCR accuracy alongside target-side translation quality. We benchmark several multimodal large language models and a dedicated TIT system in English-to-X and X-to-English settings, and find that the source language and writing system substantially affect TIT quality. Finally, we show that ImgMT is not well suited for isolating the contribution of visual information in multimodal translation.
%U https://aclanthology.org/2026.wmt-main.43/
%P 765-781

Markdown (Informal)

[ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation](https://aclanthology.org/2026.wmt-main.43/) (Uramová et al., WMT 2026)

• ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation (Uramová et al., WMT 2026)

ACL

• Šárka Uramová, Petar Petrov, Josef Jon, Ondřej Bojar, and Michal Novák. 2026. ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 765–781, Budapest, Hungary. Association for Computational Linguistics.