@inproceedings{jiang-etal-2024-mm,
title = "{MM}-{C}hat{A}lign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment",
author = "Jiang, Xuhui and
Shen, Yinghan and
Shi, Zhichao and
Xu, Chengjin and
Li, Wei and
Zihe, Huang and
Guo, Jian and
Wang, Yuanzhuo",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.148",
pages = "2637--2654",
abstract = "Multimodal entity alignment (MMEA) integrates multi-source and cross-modal knowledge graphs, a crucial yet challenging task for data-centric applications.Traditional MMEA methods derive the visual embeddings of entities and combine them with other modal data for alignment by embedding similarity comparison.However, these methods are hampered by the limited comprehension of visual attributes and deficiencies in realizing and bridging the semantics of multimodal data. To address these challenges, we propose MM-ChatAlign, a novel framework that utilizes the visual reasoning abilities of MLLMs for MMEA.The framework features an embedding-based candidate collection module that adapts to various knowledge representation strategies, effectively filtering out irrelevant reasoning candidates. Additionally, a reasoning and rethinking module, powered by MLLMs, enhances alignment by efficiently utilizing multimodal information.Extensive experiments on four MMEA datasets demonstrate MM-ChatAlign{'}s superiority and underscore the significant potential of MLLMs in MMEA tasks.The source code is available at https://github.com/jxh4945777/MMEA/.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2024-mm">
<titleInfo>
<title>MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuhui</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinghan</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhichao</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengjin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Zihe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanzhuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal entity alignment (MMEA) integrates multi-source and cross-modal knowledge graphs, a crucial yet challenging task for data-centric applications.Traditional MMEA methods derive the visual embeddings of entities and combine them with other modal data for alignment by embedding similarity comparison.However, these methods are hampered by the limited comprehension of visual attributes and deficiencies in realizing and bridging the semantics of multimodal data. To address these challenges, we propose MM-ChatAlign, a novel framework that utilizes the visual reasoning abilities of MLLMs for MMEA.The framework features an embedding-based candidate collection module that adapts to various knowledge representation strategies, effectively filtering out irrelevant reasoning candidates. Additionally, a reasoning and rethinking module, powered by MLLMs, enhances alignment by efficiently utilizing multimodal information.Extensive experiments on four MMEA datasets demonstrate MM-ChatAlign’s superiority and underscore the significant potential of MLLMs in MMEA tasks.The source code is available at https://github.com/jxh4945777/MMEA/.</abstract>
<identifier type="citekey">jiang-etal-2024-mm</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.148</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2637</start>
<end>2654</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment
%A Jiang, Xuhui
%A Shen, Yinghan
%A Shi, Zhichao
%A Xu, Chengjin
%A Li, Wei
%A Zihe, Huang
%A Guo, Jian
%A Wang, Yuanzhuo
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F jiang-etal-2024-mm
%X Multimodal entity alignment (MMEA) integrates multi-source and cross-modal knowledge graphs, a crucial yet challenging task for data-centric applications.Traditional MMEA methods derive the visual embeddings of entities and combine them with other modal data for alignment by embedding similarity comparison.However, these methods are hampered by the limited comprehension of visual attributes and deficiencies in realizing and bridging the semantics of multimodal data. To address these challenges, we propose MM-ChatAlign, a novel framework that utilizes the visual reasoning abilities of MLLMs for MMEA.The framework features an embedding-based candidate collection module that adapts to various knowledge representation strategies, effectively filtering out irrelevant reasoning candidates. Additionally, a reasoning and rethinking module, powered by MLLMs, enhances alignment by efficiently utilizing multimodal information.Extensive experiments on four MMEA datasets demonstrate MM-ChatAlign’s superiority and underscore the significant potential of MLLMs in MMEA tasks.The source code is available at https://github.com/jxh4945777/MMEA/.
%U https://aclanthology.org/2024.findings-emnlp.148
%P 2637-2654
Markdown (Informal)
[MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment](https://aclanthology.org/2024.findings-emnlp.148) (Jiang et al., Findings 2024)
ACL
- Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Huang Zihe, Jian Guo, and Yuanzhuo Wang. 2024. MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2637–2654, Miami, Florida, USA. Association for Computational Linguistics.