<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2026-learning">
    <titleInfo>
        <title>Learning to Better Exploit Visual Evidence for Multimodal Entity Linking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yingyao</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Han</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuning</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yifan</namePart>
        <namePart type="family">Xue</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiasong</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lotfi</namePart>
        <namePart type="family">Senhadji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huazhong</namePart>
        <namePart type="family">Shu</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Multimodal Entity Linking (MEL) aims to link mentions in a given context to their corresponding entities in a knowledge base by leveraging both textual and visual information. Existing MEL methods still underexploit visual information in real-world scenarios. Most approaches directly encode raw image-text inputs or apply uniform enhancement, while lacking adaptive modeling of heterogeneous mention-relevant evidence. Moreover, they typically rely on single-layer visual representations or simple cross-modal interactions, failing to capture hierarchical visual semantics required for fine-grained disambiguation. To address these limitations, we propose a novel MEL framework termed EVEMEL. First, we introduce an adaptive evidence augmentation mechanism, which analyzes the visual condition of each sample and strengthens mention-relevant discriminative clues, providing more reliable contextual evidence for entity disambiguation. Subsequently, we develop a cross-modal modeling mechanism that treats multi-layer visual representations as different semantic granularities and dynamically fuses them through token-level routing, enabling cross-modal matching. In addition, a bidirectional gated intra-modal mechanism is designed to capture multi-granularity textual and visual matching signals. Experimental results on public benchmark datasets demonstrate that the proposed EVEMEL outperforms all state-of-the-art baselines. The code is publicly available at https://github.com/hanwang86/EVEMEL.</abstract>
    <identifier type="citekey">ma-etal-2026-learning</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2088/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>47579</start>
            <end>47592</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Better Exploit Visual Evidence for Multimodal Entity Linking
%A Ma, Yingyao
%A Wang, Han
%A Wu, Yuning
%A Xue, Yifan
%A Wu, Jiasong
%A Senhadji, Lotfi
%A Shu, Huazhong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F ma-etal-2026-learning
%X Multimodal Entity Linking (MEL) aims to link mentions in a given context to their corresponding entities in a knowledge base by leveraging both textual and visual information. Existing MEL methods still underexploit visual information in real-world scenarios. Most approaches directly encode raw image-text inputs or apply uniform enhancement, while lacking adaptive modeling of heterogeneous mention-relevant evidence. Moreover, they typically rely on single-layer visual representations or simple cross-modal interactions, failing to capture hierarchical visual semantics required for fine-grained disambiguation. To address these limitations, we propose a novel MEL framework termed EVEMEL. First, we introduce an adaptive evidence augmentation mechanism, which analyzes the visual condition of each sample and strengthens mention-relevant discriminative clues, providing more reliable contextual evidence for entity disambiguation. Subsequently, we develop a cross-modal modeling mechanism that treats multi-layer visual representations as different semantic granularities and dynamically fuses them through token-level routing, enabling cross-modal matching. In addition, a bidirectional gated intra-modal mechanism is designed to capture multi-granularity textual and visual matching signals. Experimental results on public benchmark datasets demonstrate that the proposed EVEMEL outperforms all state-of-the-art baselines. The code is publicly available at https://github.com/hanwang86/EVEMEL.
%U https://aclanthology.org/2026.emnlp-main.2088/
%P 47579-47592

Markdown (Informal)

[Learning to Better Exploit Visual Evidence for Multimodal Entity Linking](https://aclanthology.org/2026.emnlp-main.2088/) (Ma et al., EMNLP 2026)

• Learning to Better Exploit Visual Evidence for Multimodal Entity Linking (Ma et al., EMNLP 2026)

ACL

• Yingyao Ma, Han Wang, Yuning Wu, Yifan Xue, Jiasong Wu, Lotfi Senhadji, and Huazhong Shu. 2026. Learning to Better Exploit Visual Evidence for Multimodal Entity Linking. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 47579–47592, Budapest, Hungary. Association for Computational Linguistics.