@inproceedings{qiu-etal-2023-sccs,
title = "{SCCS}: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment",
author = "Qiu, Jielin and
Zhu, Jiacheng and
Xu, Mengdi and
Dernoncourt, Franck and
Bui, Trung and
Wang, Zhaowen and
Li, Bo and
Zhao, Ding and
Jin, Hailin",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.101",
doi = "10.18653/v1/2023.findings-acl.101",
pages = "1584--1601",
abstract = "Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. However, existing methods extract features from the whole video and article and use fusion methods to select the representative one, thus usually ignoring the critical structure and varying semantics with video/document. In this work, we propose a Semantics-Consistent Cross-domain Summarization (SCCS) model based on optimal transport alignment with visual and textual segmentation. Our method first decomposes both videos and articles into segments in order to capture the structural semantics, and then follows a cross-domain alignment objective with optimal transport distance, which leverages multimodal interaction to match and select the visual and textual summary. We evaluated our method on three MSMO datasets, and achieved performance improvement by 8{\%} {\&} 6{\%} of textual and 6.6{\%} {\&}5.7{\%} of video summarization, respectively, which demonstrated the effectiveness of our method in producing high-quality multimodal summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2023-sccs">
<titleInfo>
<title>SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jielin</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiacheng</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengdi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaowen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ding</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. However, existing methods extract features from the whole video and article and use fusion methods to select the representative one, thus usually ignoring the critical structure and varying semantics with video/document. In this work, we propose a Semantics-Consistent Cross-domain Summarization (SCCS) model based on optimal transport alignment with visual and textual segmentation. Our method first decomposes both videos and articles into segments in order to capture the structural semantics, and then follows a cross-domain alignment objective with optimal transport distance, which leverages multimodal interaction to match and select the visual and textual summary. We evaluated our method on three MSMO datasets, and achieved performance improvement by 8% & 6% of textual and 6.6% &5.7% of video summarization, respectively, which demonstrated the effectiveness of our method in producing high-quality multimodal summaries.</abstract>
<identifier type="citekey">qiu-etal-2023-sccs</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.101</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.101</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1584</start>
<end>1601</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
%A Qiu, Jielin
%A Zhu, Jiacheng
%A Xu, Mengdi
%A Dernoncourt, Franck
%A Bui, Trung
%A Wang, Zhaowen
%A Li, Bo
%A Zhao, Ding
%A Jin, Hailin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F qiu-etal-2023-sccs
%X Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. However, existing methods extract features from the whole video and article and use fusion methods to select the representative one, thus usually ignoring the critical structure and varying semantics with video/document. In this work, we propose a Semantics-Consistent Cross-domain Summarization (SCCS) model based on optimal transport alignment with visual and textual segmentation. Our method first decomposes both videos and articles into segments in order to capture the structural semantics, and then follows a cross-domain alignment objective with optimal transport distance, which leverages multimodal interaction to match and select the visual and textual summary. We evaluated our method on three MSMO datasets, and achieved performance improvement by 8% & 6% of textual and 6.6% &5.7% of video summarization, respectively, which demonstrated the effectiveness of our method in producing high-quality multimodal summaries.
%R 10.18653/v1/2023.findings-acl.101
%U https://aclanthology.org/2023.findings-acl.101
%U https://doi.org/10.18653/v1/2023.findings-acl.101
%P 1584-1601
Markdown (Informal)
[SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment](https://aclanthology.org/2023.findings-acl.101) (Qiu et al., Findings 2023)
ACL
- Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, and Hailin Jin. 2023. SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1584–1601, Toronto, Canada. Association for Computational Linguistics.