@inproceedings{fu-etal-2021-mm,
title = "{MM}-{AVS}: A Full-Scale Dataset for Multi-modal Summarization",
author = "Fu, Xiyan and
Wang, Jun and
Yang, Zhenglu",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.473",
doi = "10.18653/v1/2021.naacl-main.473",
pages = "5922--5926",
abstract = "Multimodal summarization becomes increasingly significant as it is the basis for question answering, Web search, and many other downstream tasks. However, its learning materials have been lacking a holistic organization by integrating resources from various modalities, thereby lagging behind the research progress of this field. In this study, we release a full-scale multimodal dataset comprehensively gathering documents, summaries, images, captions, videos, audios, transcripts, and titles in English from CNN and Daily Mail. To our best knowledge, this is the first collection that spans all modalities and nearly comprises all types of materials available in this community. In addition, we devise a baseline model based on the novel dataset, which employs a newly proposed Jump-Attention mechanism based on transcripts. The experimental results validate the important assistance role of the external information for multimodal summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2021-mm">
<titleInfo>
<title>MM-AVS: A Full-Scale Dataset for Multi-modal Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenglu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal summarization becomes increasingly significant as it is the basis for question answering, Web search, and many other downstream tasks. However, its learning materials have been lacking a holistic organization by integrating resources from various modalities, thereby lagging behind the research progress of this field. In this study, we release a full-scale multimodal dataset comprehensively gathering documents, summaries, images, captions, videos, audios, transcripts, and titles in English from CNN and Daily Mail. To our best knowledge, this is the first collection that spans all modalities and nearly comprises all types of materials available in this community. In addition, we devise a baseline model based on the novel dataset, which employs a newly proposed Jump-Attention mechanism based on transcripts. The experimental results validate the important assistance role of the external information for multimodal summarization.</abstract>
<identifier type="citekey">fu-etal-2021-mm</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.473</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.473</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5922</start>
<end>5926</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MM-AVS: A Full-Scale Dataset for Multi-modal Summarization
%A Fu, Xiyan
%A Wang, Jun
%A Yang, Zhenglu
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F fu-etal-2021-mm
%X Multimodal summarization becomes increasingly significant as it is the basis for question answering, Web search, and many other downstream tasks. However, its learning materials have been lacking a holistic organization by integrating resources from various modalities, thereby lagging behind the research progress of this field. In this study, we release a full-scale multimodal dataset comprehensively gathering documents, summaries, images, captions, videos, audios, transcripts, and titles in English from CNN and Daily Mail. To our best knowledge, this is the first collection that spans all modalities and nearly comprises all types of materials available in this community. In addition, we devise a baseline model based on the novel dataset, which employs a newly proposed Jump-Attention mechanism based on transcripts. The experimental results validate the important assistance role of the external information for multimodal summarization.
%R 10.18653/v1/2021.naacl-main.473
%U https://aclanthology.org/2021.naacl-main.473
%U https://doi.org/10.18653/v1/2021.naacl-main.473
%P 5922-5926
Markdown (Informal)
[MM-AVS: A Full-Scale Dataset for Multi-modal Summarization](https://aclanthology.org/2021.naacl-main.473) (Fu et al., NAACL 2021)
ACL
- Xiyan Fu, Jun Wang, and Zhenglu Yang. 2021. MM-AVS: A Full-Scale Dataset for Multi-modal Summarization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5922–5926, Online. Association for Computational Linguistics.