@inproceedings{huang-etal-2024-mner,
title = "{MNER}-{MI}: A Multi-image Dataset for Multimodal Named Entity Recognition in Social Media",
author = "Huang, Shizhou and
Xu, Bo and
Li, Changqun and
Ye, Jiabo and
Lin, Xin",
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.1001",
pages = "11452--11462",
abstract = "Recently, multimodal named entity recognition (MNER) has emerged as a vital research area within named entity recognition. However, current MNER datasets and methods are predominantly based on text and a single accompanying image, leaving a significant research gap in MNER scenarios involving multiple images. To address the critical research gap and enhance the scope of MNER for real-world applications, we propose a novel human-annotated MNER dataset with multiple images called MNER-MI. Additionally, we construct a dataset named MNER-MI-Plus, derived from MNER-MI, to ensure its generality and applicability. Based on these datasets, we establish a comprehensive set of strong and representative baselines and we further propose a simple temporal prompt model with multiple images to address the new challenges in multi-image scenarios. We have conducted extensive experiments to demonstrate that considering multiple images provides a significant improvement over a single image and can offer substantial benefits for MNER. Furthermore, our proposed method achieves state-of-the-art results on both MNER-MI and MNER-MI-Plus, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MNER-MI.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2024-mner">
<titleInfo>
<title>MNER-MI: A Multi-image Dataset for Multimodal Named Entity Recognition in Social Media</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">Jiabo</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Lin</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>Recently, multimodal named entity recognition (MNER) has emerged as a vital research area within named entity recognition. However, current MNER datasets and methods are predominantly based on text and a single accompanying image, leaving a significant research gap in MNER scenarios involving multiple images. To address the critical research gap and enhance the scope of MNER for real-world applications, we propose a novel human-annotated MNER dataset with multiple images called MNER-MI. Additionally, we construct a dataset named MNER-MI-Plus, derived from MNER-MI, to ensure its generality and applicability. Based on these datasets, we establish a comprehensive set of strong and representative baselines and we further propose a simple temporal prompt model with multiple images to address the new challenges in multi-image scenarios. We have conducted extensive experiments to demonstrate that considering multiple images provides a significant improvement over a single image and can offer substantial benefits for MNER. Furthermore, our proposed method achieves state-of-the-art results on both MNER-MI and MNER-MI-Plus, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MNER-MI.</abstract>
<identifier type="citekey">huang-etal-2024-mner</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1001</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11452</start>
<end>11462</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MNER-MI: A Multi-image Dataset for Multimodal Named Entity Recognition in Social Media
%A Huang, Shizhou
%A Xu, Bo
%A Li, Changqun
%A Ye, Jiabo
%A Lin, Xin
%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 huang-etal-2024-mner
%X Recently, multimodal named entity recognition (MNER) has emerged as a vital research area within named entity recognition. However, current MNER datasets and methods are predominantly based on text and a single accompanying image, leaving a significant research gap in MNER scenarios involving multiple images. To address the critical research gap and enhance the scope of MNER for real-world applications, we propose a novel human-annotated MNER dataset with multiple images called MNER-MI. Additionally, we construct a dataset named MNER-MI-Plus, derived from MNER-MI, to ensure its generality and applicability. Based on these datasets, we establish a comprehensive set of strong and representative baselines and we further propose a simple temporal prompt model with multiple images to address the new challenges in multi-image scenarios. We have conducted extensive experiments to demonstrate that considering multiple images provides a significant improvement over a single image and can offer substantial benefits for MNER. Furthermore, our proposed method achieves state-of-the-art results on both MNER-MI and MNER-MI-Plus, demonstrating its effectiveness. The datasets and source code can be found at https://github.com/JinFish/MNER-MI.
%U https://aclanthology.org/2024.lrec-main.1001
%P 11452-11462
Markdown (Informal)
[MNER-MI: A Multi-image Dataset for Multimodal Named Entity Recognition in Social Media](https://aclanthology.org/2024.lrec-main.1001) (Huang et al., LREC-COLING 2024)
ACL