@inproceedings{li-etal-2023-multi-modal-knowledge,
title = "Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment",
author = "Li, Qian and
Ji, Cheng and
Guo, Shu and
Liang, Zhaoji and
Wang, Lihong and
Li, Jianxin",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.70",
doi = "10.18653/v1/2023.findings-emnlp.70",
pages = "987--999",
abstract = "Multi-Modal Entity Alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs). However, this task faces challenges due to the presence of different types of information, including neighboring entities, multi-modal attributes, and entity types. Directly incorporating the above information (e.g., concatenation or attention) can lead to an unaligned information space. To address these challenges, we propose a novel MMEA transformer, called Meaformer, that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task. Taking advantage of the transformer{'}s ability to better integrate multiple information, we design a hierarchical modifiable self-attention block in a transformer encoder to preserve the unique semantics of different information. Furthermore, we design two entity-type prefix injection methods to redintegrate entity-type information using type prefixes, which help to restrict the global information of entities not present in the MMKGs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-multi-modal-knowledge">
<titleInfo>
<title>Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoji</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lihong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-Modal Entity Alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs). However, this task faces challenges due to the presence of different types of information, including neighboring entities, multi-modal attributes, and entity types. Directly incorporating the above information (e.g., concatenation or attention) can lead to an unaligned information space. To address these challenges, we propose a novel MMEA transformer, called Meaformer, that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task. Taking advantage of the transformer’s ability to better integrate multiple information, we design a hierarchical modifiable self-attention block in a transformer encoder to preserve the unique semantics of different information. Furthermore, we design two entity-type prefix injection methods to redintegrate entity-type information using type prefixes, which help to restrict the global information of entities not present in the MMKGs.</abstract>
<identifier type="citekey">li-etal-2023-multi-modal-knowledge</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.70</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.70</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>987</start>
<end>999</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment
%A Li, Qian
%A Ji, Cheng
%A Guo, Shu
%A Liang, Zhaoji
%A Wang, Lihong
%A Li, Jianxin
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-multi-modal-knowledge
%X Multi-Modal Entity Alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs). However, this task faces challenges due to the presence of different types of information, including neighboring entities, multi-modal attributes, and entity types. Directly incorporating the above information (e.g., concatenation or attention) can lead to an unaligned information space. To address these challenges, we propose a novel MMEA transformer, called Meaformer, that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task. Taking advantage of the transformer’s ability to better integrate multiple information, we design a hierarchical modifiable self-attention block in a transformer encoder to preserve the unique semantics of different information. Furthermore, we design two entity-type prefix injection methods to redintegrate entity-type information using type prefixes, which help to restrict the global information of entities not present in the MMKGs.
%R 10.18653/v1/2023.findings-emnlp.70
%U https://aclanthology.org/2023.findings-emnlp.70
%U https://doi.org/10.18653/v1/2023.findings-emnlp.70
%P 987-999
Markdown (Informal)
[Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment](https://aclanthology.org/2023.findings-emnlp.70) (Li et al., Findings 2023)
ACL