@inproceedings{xiaorui-2023-mcls,
title = "{MCLS}: A Large-Scale Multimodal Cross-Lingual Summarization Dataset",
author = "Xiaorui, Shi",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.73/",
pages = "862--874",
language = "eng",
abstract = "{\textquotedblleft}Multimodal summarization which aims to generate summaries with multimodal inputs, e.g., textand visual features, has attracted much attention in the research community. However, previousstudies only focus on monolingual multimodal summarization and neglect the non-native readerto understand the cross-lingual news in practical applications. It inspires us to present a newtask, named Multimodal Cross-Lingual Summarization for news (MCLS), which generates cross-lingual summaries from multi-source information. To this end, we present a large-scale multimodalcross-lingual summarization dataset, which consists of 1.1 million article-summary pairs with 3.4million images in 44 * 43 language pairs. To generate a summary in any language, we propose aunified framework that jointly trains the multimodal monolingual and cross-lingual summarizationtasks, where a bi-directional knowledge distillation approach is designed to transfer knowledgebetween both tasks. Extensive experiments on many-to-many settings show the effectiveness ofthe proposed model.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiaorui-2023-mcls">
<titleInfo>
<title>MCLS: A Large-Scale Multimodal Cross-Lingual Summarization Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Xiaorui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Multimodal summarization which aims to generate summaries with multimodal inputs, e.g., textand visual features, has attracted much attention in the research community. However, previousstudies only focus on monolingual multimodal summarization and neglect the non-native readerto understand the cross-lingual news in practical applications. It inspires us to present a newtask, named Multimodal Cross-Lingual Summarization for news (MCLS), which generates cross-lingual summaries from multi-source information. To this end, we present a large-scale multimodalcross-lingual summarization dataset, which consists of 1.1 million article-summary pairs with 3.4million images in 44 * 43 language pairs. To generate a summary in any language, we propose aunified framework that jointly trains the multimodal monolingual and cross-lingual summarizationtasks, where a bi-directional knowledge distillation approach is designed to transfer knowledgebetween both tasks. Extensive experiments on many-to-many settings show the effectiveness ofthe proposed model.”</abstract>
<identifier type="citekey">xiaorui-2023-mcls</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.73/</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>862</start>
<end>874</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MCLS: A Large-Scale Multimodal Cross-Lingual Summarization Dataset
%A Xiaorui, Shi
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G eng
%F xiaorui-2023-mcls
%X “Multimodal summarization which aims to generate summaries with multimodal inputs, e.g., textand visual features, has attracted much attention in the research community. However, previousstudies only focus on monolingual multimodal summarization and neglect the non-native readerto understand the cross-lingual news in practical applications. It inspires us to present a newtask, named Multimodal Cross-Lingual Summarization for news (MCLS), which generates cross-lingual summaries from multi-source information. To this end, we present a large-scale multimodalcross-lingual summarization dataset, which consists of 1.1 million article-summary pairs with 3.4million images in 44 * 43 language pairs. To generate a summary in any language, we propose aunified framework that jointly trains the multimodal monolingual and cross-lingual summarizationtasks, where a bi-directional knowledge distillation approach is designed to transfer knowledgebetween both tasks. Extensive experiments on many-to-many settings show the effectiveness ofthe proposed model.”
%U https://aclanthology.org/2023.ccl-1.73/
%P 862-874
Markdown (Informal)
[MCLS: A Large-Scale Multimodal Cross-Lingual Summarization Dataset](https://aclanthology.org/2023.ccl-1.73/) (Xiaorui, CCL 2023)
ACL