@inproceedings{wang-etal-2022-n24news,
title = "{N}24{N}ews: A New Dataset for Multimodal News Classification",
author = "Wang, Zhen and
Shan, Xu and
Zhang, Xiangxie and
Yang, Jie",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.729",
pages = "6768--6775",
abstract = "Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification. In this paper, we propose a new dataset, N24News, which is generated from New York Times with 24 categories and contains both text and image information in each news. We use a multitask multimodal method and the experimental results show multimodal news classification performs better than text-only news classification. Depending on the length of the text, the classification accuracy can be increased by up to 8.11{\%}. Our research reveals the relationship between the performance of a multimodal classifier and its sub-classifiers, and also the possible improvements when applying multimodal in news classification. N24News is shown to have great potential to prompt the multimodal news studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-n24news">
<titleInfo>
<title>N24News: A New Dataset for Multimodal News Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Shan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangxie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification. In this paper, we propose a new dataset, N24News, which is generated from New York Times with 24 categories and contains both text and image information in each news. We use a multitask multimodal method and the experimental results show multimodal news classification performs better than text-only news classification. Depending on the length of the text, the classification accuracy can be increased by up to 8.11%. Our research reveals the relationship between the performance of a multimodal classifier and its sub-classifiers, and also the possible improvements when applying multimodal in news classification. N24News is shown to have great potential to prompt the multimodal news studies.</abstract>
<identifier type="citekey">wang-etal-2022-n24news</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.729</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6768</start>
<end>6775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T N24News: A New Dataset for Multimodal News Classification
%A Wang, Zhen
%A Shan, Xu
%A Zhang, Xiangxie
%A Yang, Jie
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F wang-etal-2022-n24news
%X Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification. In this paper, we propose a new dataset, N24News, which is generated from New York Times with 24 categories and contains both text and image information in each news. We use a multitask multimodal method and the experimental results show multimodal news classification performs better than text-only news classification. Depending on the length of the text, the classification accuracy can be increased by up to 8.11%. Our research reveals the relationship between the performance of a multimodal classifier and its sub-classifiers, and also the possible improvements when applying multimodal in news classification. N24News is shown to have great potential to prompt the multimodal news studies.
%U https://aclanthology.org/2022.lrec-1.729
%P 6768-6775
Markdown (Informal)
[N24News: A New Dataset for Multimodal News Classification](https://aclanthology.org/2022.lrec-1.729) (Wang et al., LREC 2022)
ACL