@inproceedings{cheng-etal-2025-sgmea,
title = "{SGMEA}: Structure-Guided Multimodal Entity Alignment",
author = "Cheng, Jingwei and
Guo, Mingxiao and
Zhang, Fu",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.525/",
pages = "7851--7861",
abstract = "Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different multimodal knowledge graphs (MMKGs) by integrating structural information, entity attributes, and visual data, thereby promoting knowledge sharing and deep multimodal data integration. However, existing methods often overlook the deeper connections between multimodal data. They primarily focus on the interactions between neighboring entities in the structural modality while neglecting the interactions between entities in the visual and attribute modalities. To address this, we propose a structure-guided multimodal entity alignment method (SGMEA), which prioritizes structural information from knowledge graphs to enhance the visual and attribute modalities. By fusing multimodal representations, SGMEA improves the accuracy of entity alignment. Experimental results demonstrate that SGMEA achieves stateof-the-art performance across multiple datasets, validating its effectiveness and superiority in practical applications."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2025-sgmea">
<titleInfo>
<title>SGMEA: Structure-Guided Multimodal Entity Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxiao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different multimodal knowledge graphs (MMKGs) by integrating structural information, entity attributes, and visual data, thereby promoting knowledge sharing and deep multimodal data integration. However, existing methods often overlook the deeper connections between multimodal data. They primarily focus on the interactions between neighboring entities in the structural modality while neglecting the interactions between entities in the visual and attribute modalities. To address this, we propose a structure-guided multimodal entity alignment method (SGMEA), which prioritizes structural information from knowledge graphs to enhance the visual and attribute modalities. By fusing multimodal representations, SGMEA improves the accuracy of entity alignment. Experimental results demonstrate that SGMEA achieves stateof-the-art performance across multiple datasets, validating its effectiveness and superiority in practical applications.</abstract>
<identifier type="citekey">cheng-etal-2025-sgmea</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.525/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>7851</start>
<end>7861</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SGMEA: Structure-Guided Multimodal Entity Alignment
%A Cheng, Jingwei
%A Guo, Mingxiao
%A Zhang, Fu
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F cheng-etal-2025-sgmea
%X Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different multimodal knowledge graphs (MMKGs) by integrating structural information, entity attributes, and visual data, thereby promoting knowledge sharing and deep multimodal data integration. However, existing methods often overlook the deeper connections between multimodal data. They primarily focus on the interactions between neighboring entities in the structural modality while neglecting the interactions between entities in the visual and attribute modalities. To address this, we propose a structure-guided multimodal entity alignment method (SGMEA), which prioritizes structural information from knowledge graphs to enhance the visual and attribute modalities. By fusing multimodal representations, SGMEA improves the accuracy of entity alignment. Experimental results demonstrate that SGMEA achieves stateof-the-art performance across multiple datasets, validating its effectiveness and superiority in practical applications.
%U https://aclanthology.org/2025.coling-main.525/
%P 7851-7861
Markdown (Informal)
[SGMEA: Structure-Guided Multimodal Entity Alignment](https://aclanthology.org/2025.coling-main.525/) (Cheng et al., COLING 2025)
ACL
- Jingwei Cheng, Mingxiao Guo, and Fu Zhang. 2025. SGMEA: Structure-Guided Multimodal Entity Alignment. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7851–7861, Abu Dhabi, UAE. Association for Computational Linguistics.