@inproceedings{long-etal-2024-trust,
title = "Trust in Internal or External Knowledge? Generative Multi-Modal Entity Linking with Knowledge Retriever",
author = "Long, Xinwei and
Zeng, Jiali and
Meng, Fandong and
Zhou, Jie and
Zhou, Bowen",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.450",
pages = "7559--7569",
abstract = "Multi-modal entity linking (MEL) is a challenging task that requires accurate prediction of entities within extensive search spaces, utilizing multi-modal contexts. Existing generative approaches struggle with the knowledge gap between visual entity information and the intrinsic parametric knowledge of LLMs. To address this knowledge gap, we introduce a novel approach called GELR, which incorporates a knowledge retriever to enhance visual entity information by leveraging external sources. Additionally, we devise a prioritization scheme that effectively handles noisy retrieval results and manages conflicts arising from the integration of external and internal knowledge. Moreover, we propose a noise-aware instruction tuning technique during training to finely adjust the model{'}s ability to leverage retrieved information effectively. Through extensive experiments conducted on three benchmarks, our approach showcases remarkable improvements, ranging from 3.0{\%} to 6.5{\%}, across all evaluation metrics compared to strong baselines. These results demonstrate the effectiveness and superiority of our proposed method in tackling the complexities of multi-modal entity linking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-etal-2024-trust">
<titleInfo>
<title>Trust in Internal or External Knowledge? Generative Multi-Modal Entity Linking with Knowledge Retriever</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinwei</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiali</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal entity linking (MEL) is a challenging task that requires accurate prediction of entities within extensive search spaces, utilizing multi-modal contexts. Existing generative approaches struggle with the knowledge gap between visual entity information and the intrinsic parametric knowledge of LLMs. To address this knowledge gap, we introduce a novel approach called GELR, which incorporates a knowledge retriever to enhance visual entity information by leveraging external sources. Additionally, we devise a prioritization scheme that effectively handles noisy retrieval results and manages conflicts arising from the integration of external and internal knowledge. Moreover, we propose a noise-aware instruction tuning technique during training to finely adjust the model’s ability to leverage retrieved information effectively. Through extensive experiments conducted on three benchmarks, our approach showcases remarkable improvements, ranging from 3.0% to 6.5%, across all evaluation metrics compared to strong baselines. These results demonstrate the effectiveness and superiority of our proposed method in tackling the complexities of multi-modal entity linking.</abstract>
<identifier type="citekey">long-etal-2024-trust</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.450</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7559</start>
<end>7569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trust in Internal or External Knowledge? Generative Multi-Modal Entity Linking with Knowledge Retriever
%A Long, Xinwei
%A Zeng, Jiali
%A Meng, Fandong
%A Zhou, Jie
%A Zhou, Bowen
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F long-etal-2024-trust
%X Multi-modal entity linking (MEL) is a challenging task that requires accurate prediction of entities within extensive search spaces, utilizing multi-modal contexts. Existing generative approaches struggle with the knowledge gap between visual entity information and the intrinsic parametric knowledge of LLMs. To address this knowledge gap, we introduce a novel approach called GELR, which incorporates a knowledge retriever to enhance visual entity information by leveraging external sources. Additionally, we devise a prioritization scheme that effectively handles noisy retrieval results and manages conflicts arising from the integration of external and internal knowledge. Moreover, we propose a noise-aware instruction tuning technique during training to finely adjust the model’s ability to leverage retrieved information effectively. Through extensive experiments conducted on three benchmarks, our approach showcases remarkable improvements, ranging from 3.0% to 6.5%, across all evaluation metrics compared to strong baselines. These results demonstrate the effectiveness and superiority of our proposed method in tackling the complexities of multi-modal entity linking.
%U https://aclanthology.org/2024.findings-acl.450
%P 7559-7569
Markdown (Informal)
[Trust in Internal or External Knowledge? Generative Multi-Modal Entity Linking with Knowledge Retriever](https://aclanthology.org/2024.findings-acl.450) (Long et al., Findings 2024)
ACL