MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking

Sathyanarayanan Ramamoorthy; Vishwa Shah; Simran Khanuja; Zaid Sheikh; Shan Jie; Ann Chia; Shearman Chua; Graham Neubig

doi:10.1162/tacl.a.633

MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking

Sathyanarayanan Ramamoorthy, Vishwa Shah, Simran Khanuja, Zaid Sheikh, Shan Jie, Ann Chia, Shearman Chua, Graham Neubig

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 <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

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

This paper introduces MERLIN, a novel testbed system for the task of Multilingual Multimodal Entity Linking. The created dataset includes BBC news article titles, paired with corresponding images, in five languages: Hindi, Japanese, Indonesian, Vietnamese, and Tamil, featuring over 7,000 named entity mentions linked to 2,500 unique Wikidata entities. We also include several benchmarks using multilingual and multimodal entity linking methods exploring different language models like LLaMa-2 and Aya-23. Our findings indicate that incorporating visual data improves the accuracy of entity linking, especially for entities where the textual context is ambiguous or insufficient, and particularly for models that do not have strong multilingual abilities. For the work, the dataset, methods are available online.1

Anthology ID:: 2026.tacl-1.19
Volume:: Transactions of the Association for Computational Linguistics, Volume 14
Month:
Year:: 2026
Address:: Cambridge, MA
Venue:: TACL
SIG:
Publisher:: MIT Press
Note:
Pages:: 399–417
Language:
URL:: https://aclanthology.org/2026.tacl-1.19/
DOI:: 10.1162/tacl.a.633
Bibkey:
Cite (ACL):: Sathyanarayanan Ramamoorthy, Vishwa Shah, Simran Khanuja, Zaid Sheikh, Shan Jie, Ann Chia, Shearman Chua, and Graham Neubig. 2026. MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking. Transactions of the Association for Computational Linguistics, 14:399–417.
Cite (Informal):: MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking (Ramamoorthy et al., TACL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.tacl-1.19.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@article{ramamoorthy-etal-2026-merlin,
    title = "{MERLIN}: A Testbed for Multilingual Multimodal Entity Recognition and Linking",
    author = "Ramamoorthy, Sathyanarayanan  and
      Shah, Vishwa  and
      Khanuja, Simran  and
      Sheikh, Zaid  and
      Jie, Shan  and
      Chia, Ann  and
      Chua, Shearman  and
      Neubig, Graham",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2026.tacl-1.19/",
    doi = "10.1162/tacl.a.633",
    pages = "399--417",
    abstract = "This paper introduces MERLIN, a novel testbed system for the task of Multilingual Multimodal Entity Linking. The created dataset includes BBC news article titles, paired with corresponding images, in five languages: Hindi, Japanese, Indonesian, Vietnamese, and Tamil, featuring over 7,000 named entity mentions linked to 2,500 unique Wikidata entities. We also include several benchmarks using multilingual and multimodal entity linking methods exploring different language models like LLaMa-2 and Aya-23. Our findings indicate that incorporating visual data improves the accuracy of entity linking, especially for entities where the textual context is ambiguous or insufficient, and particularly for models that do not have strong multilingual abilities. For the work, the dataset, methods are available online.1"
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramamoorthy-etal-2026-merlin">
    <titleInfo>
        <title>MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sathyanarayanan</namePart>
        <namePart type="family">Ramamoorthy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vishwa</namePart>
        <namePart type="family">Shah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Simran</namePart>
        <namePart type="family">Khanuja</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zaid</namePart>
        <namePart type="family">Sheikh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shan</namePart>
        <namePart type="family">Jie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ann</namePart>
        <namePart type="family">Chia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shearman</namePart>
        <namePart type="family">Chua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>This paper introduces MERLIN, a novel testbed system for the task of Multilingual Multimodal Entity Linking. The created dataset includes BBC news article titles, paired with corresponding images, in five languages: Hindi, Japanese, Indonesian, Vietnamese, and Tamil, featuring over 7,000 named entity mentions linked to 2,500 unique Wikidata entities. We also include several benchmarks using multilingual and multimodal entity linking methods exploring different language models like LLaMa-2 and Aya-23. Our findings indicate that incorporating visual data improves the accuracy of entity linking, especially for entities where the textual context is ambiguous or insufficient, and particularly for models that do not have strong multilingual abilities. For the work, the dataset, methods are available online.1</abstract>
    <identifier type="citekey">ramamoorthy-etal-2026-merlin</identifier>
    <identifier type="doi">10.1162/tacl.a.633</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.19/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>399</start>
            <end>417</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Journal Article
%T MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking
%A Ramamoorthy, Sathyanarayanan
%A Shah, Vishwa
%A Khanuja, Simran
%A Sheikh, Zaid
%A Jie, Shan
%A Chia, Ann
%A Chua, Shearman
%A Neubig, Graham
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F ramamoorthy-etal-2026-merlin
%X This paper introduces MERLIN, a novel testbed system for the task of Multilingual Multimodal Entity Linking. The created dataset includes BBC news article titles, paired with corresponding images, in five languages: Hindi, Japanese, Indonesian, Vietnamese, and Tamil, featuring over 7,000 named entity mentions linked to 2,500 unique Wikidata entities. We also include several benchmarks using multilingual and multimodal entity linking methods exploring different language models like LLaMa-2 and Aya-23. Our findings indicate that incorporating visual data improves the accuracy of entity linking, especially for entities where the textual context is ambiguous or insufficient, and particularly for models that do not have strong multilingual abilities. For the work, the dataset, methods are available online.1
%R 10.1162/tacl.a.633
%U https://aclanthology.org/2026.tacl-1.19/
%U https://doi.org/10.1162/tacl.a.633
%P 399-417

Download as File

Markdown (Informal)

[MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking](https://aclanthology.org/2026.tacl-1.19/) (Ramamoorthy et al., TACL 2026)

MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking (Ramamoorthy et al., TACL 2026)

ACL

Sathyanarayanan Ramamoorthy, Vishwa Shah, Simran Khanuja, Zaid Sheikh, Shan Jie, Ann Chia, Shearman Chua, and Graham Neubig. 2026. MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking. Transactions of the Association for Computational Linguistics, 14:399–417.