@inproceedings{zheng-etal-2024-decompose,
title = "Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition",
author = "Zheng, Zihao and
Zhang, Zihan and
Wang, Zexin and
Fu, Ruiji and
Liu, Ming and
Wang, Zhongyuan and
Qin, Bing",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.403/",
pages = "4498--4508",
abstract = "Multi-modal Named Entity Recognition, a fundamental task for multi-modal knowledge graph construction, requires integrating multi-modal information to extract named entities from text. Previous research has explored the integration of multi-modal representations at different granularities. However, they struggle to integrate all these multi-modal representations to provide rich contextual information to improve multi-modal named entity recognition. In this paper, we propose DPE-MNER, which is an iterative reasoning framework that dynamically incorporates all the diverse multi-modal representations following the strategy of {\textquotedblleft}decompose, prioritize, and eliminate{\textquotedblright}. Within the framework, the fusion of diverse multi-modal representations is \textbf{decomposed} into hierarchically connected fusion layers that are easier to handle. The incorporation of multi-modal information \textbf{prioritizes} transitioning from {\textquotedblleft}easy-to-hard{\textquotedblright} and {\textquotedblleft}coarse-to-fine{\textquotedblright}. The explicit modeling of cross-modal relevance \textbf{eliminate} the irrelevances that will mislead the MNER prediction. Extensive experiments on two public datasets have demonstrated the effectiveness of our approach."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2024-decompose">
<titleInfo>
<title>Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zexin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiji</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal Named Entity Recognition, a fundamental task for multi-modal knowledge graph construction, requires integrating multi-modal information to extract named entities from text. Previous research has explored the integration of multi-modal representations at different granularities. However, they struggle to integrate all these multi-modal representations to provide rich contextual information to improve multi-modal named entity recognition. In this paper, we propose DPE-MNER, which is an iterative reasoning framework that dynamically incorporates all the diverse multi-modal representations following the strategy of “decompose, prioritize, and eliminate”. Within the framework, the fusion of diverse multi-modal representations is decomposed into hierarchically connected fusion layers that are easier to handle. The incorporation of multi-modal information prioritizes transitioning from “easy-to-hard” and “coarse-to-fine”. The explicit modeling of cross-modal relevance eliminate the irrelevances that will mislead the MNER prediction. Extensive experiments on two public datasets have demonstrated the effectiveness of our approach.</abstract>
<identifier type="citekey">zheng-etal-2024-decompose</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.403/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4498</start>
<end>4508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition
%A Zheng, Zihao
%A Zhang, Zihan
%A Wang, Zexin
%A Fu, Ruiji
%A Liu, Ming
%A Wang, Zhongyuan
%A Qin, Bing
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zheng-etal-2024-decompose
%X Multi-modal Named Entity Recognition, a fundamental task for multi-modal knowledge graph construction, requires integrating multi-modal information to extract named entities from text. Previous research has explored the integration of multi-modal representations at different granularities. However, they struggle to integrate all these multi-modal representations to provide rich contextual information to improve multi-modal named entity recognition. In this paper, we propose DPE-MNER, which is an iterative reasoning framework that dynamically incorporates all the diverse multi-modal representations following the strategy of “decompose, prioritize, and eliminate”. Within the framework, the fusion of diverse multi-modal representations is decomposed into hierarchically connected fusion layers that are easier to handle. The incorporation of multi-modal information prioritizes transitioning from “easy-to-hard” and “coarse-to-fine”. The explicit modeling of cross-modal relevance eliminate the irrelevances that will mislead the MNER prediction. Extensive experiments on two public datasets have demonstrated the effectiveness of our approach.
%U https://aclanthology.org/2024.lrec-main.403/
%P 4498-4508
Markdown (Informal)
[Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition](https://aclanthology.org/2024.lrec-main.403/) (Zheng et al., LREC-COLING 2024)
ACL
- Zihao Zheng, Zihan Zhang, Zexin Wang, Ruiji Fu, Ming Liu, Zhongyuan Wang, and Bing Qin. 2024. Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4498–4508, Torino, Italia. ELRA and ICCL.