@inproceedings{huang-etal-2025-mre,
title = "{MRE}-{MI}: A Multi-image Dataset for Multimodal Relation Extraction in Social Media Posts",
author = "Huang, Shizhou and
Xu, Bo and
Li, Changqun and
Yu, Yang and
Lin, Xin Alex",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.351/",
doi = "10.18653/v1/2025.findings-naacl.351",
pages = "6267--6277",
ISBN = "979-8-89176-195-7",
abstract = "Despite recent advances in Multimodal Relation Extraction (MRE), existing datasets and approaches primarily focus on single-image scenarios, overlooking the prevalent real-world cases where relationships are expressed through multiple images alongside text. To address this limitation, we present MRE-MI, a novel human-annotated dataset that includes both multi-image and single-image instances for relation extraction. Beyond dataset creation, we establish comprehensive baselines and propose a simple model named Global and Local Relevance-Modulated Attention Model (GLRA) to address the new challenges in multi-image scenarios. Our extensive experiments reveal that incorporating multiple images substantially improves relation extraction in multi-image scenarios. Furthermore, GLRA achieves state-of-the-art results on MRE-MI, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MRE-MI."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2025-mre">
<titleInfo>
<title>MRE-MI: A Multi-image Dataset for Multimodal Relation Extraction in Social Media Posts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shizhou</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changqun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="given">Alex</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Despite recent advances in Multimodal Relation Extraction (MRE), existing datasets and approaches primarily focus on single-image scenarios, overlooking the prevalent real-world cases where relationships are expressed through multiple images alongside text. To address this limitation, we present MRE-MI, a novel human-annotated dataset that includes both multi-image and single-image instances for relation extraction. Beyond dataset creation, we establish comprehensive baselines and propose a simple model named Global and Local Relevance-Modulated Attention Model (GLRA) to address the new challenges in multi-image scenarios. Our extensive experiments reveal that incorporating multiple images substantially improves relation extraction in multi-image scenarios. Furthermore, GLRA achieves state-of-the-art results on MRE-MI, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MRE-MI.</abstract>
<identifier type="citekey">huang-etal-2025-mre</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.351</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.351/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6267</start>
<end>6277</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MRE-MI: A Multi-image Dataset for Multimodal Relation Extraction in Social Media Posts
%A Huang, Shizhou
%A Xu, Bo
%A Li, Changqun
%A Yu, Yang
%A Lin, Xin Alex
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F huang-etal-2025-mre
%X Despite recent advances in Multimodal Relation Extraction (MRE), existing datasets and approaches primarily focus on single-image scenarios, overlooking the prevalent real-world cases where relationships are expressed through multiple images alongside text. To address this limitation, we present MRE-MI, a novel human-annotated dataset that includes both multi-image and single-image instances for relation extraction. Beyond dataset creation, we establish comprehensive baselines and propose a simple model named Global and Local Relevance-Modulated Attention Model (GLRA) to address the new challenges in multi-image scenarios. Our extensive experiments reveal that incorporating multiple images substantially improves relation extraction in multi-image scenarios. Furthermore, GLRA achieves state-of-the-art results on MRE-MI, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MRE-MI.
%R 10.18653/v1/2025.findings-naacl.351
%U https://aclanthology.org/2025.findings-naacl.351/
%U https://doi.org/10.18653/v1/2025.findings-naacl.351
%P 6267-6277
Markdown (Informal)
[MRE-MI: A Multi-image Dataset for Multimodal Relation Extraction in Social Media Posts](https://aclanthology.org/2025.findings-naacl.351/) (Huang et al., Findings 2025)
ACL