@inproceedings{hirao-etal-2024-video,
title = "Video Discourse Parsing and Its Application to Multimodal Summarization: A Dataset and Baseline Approaches",
author = "Hirao, Tsutomu and
Kobayashi, Naoki and
Kamigaito, Hidetaka and
Okumura, Manabu and
Kimura, Akisato",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.581/",
doi = "10.18653/v1/2024.findings-emnlp.581",
pages = "9943--9958",
abstract = "This paper tackles a new task: discourse parsing for videos, inspired by text discourse parsing based on Rhetorical Structure Theory (RST). The task aims to construct an RST tree for a video to represent its storyline and illustrate the event relationships. We first construct a benchmark dataset by identifying events with their time spans, providing corresponding captions, and constructing RST trees with events as leaves. We then evaluate baseline approaches to video RST parsing: the {\textquoteleft}parsing after captioning' framework and parsing via visual features. The results show that a parser using gold captions performed the best, while parsers relying on generated captions performed the worst; a parser using visual features provided intermediate performance. However, we observed that parsing via visual features could be improved by pre-training it with video captioning designed to produce a coherent video story. Furthermore, we demonstrated that RST trees obtained from videos contribute to multimodal summarization consisting of keyframes with texts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hirao-etal-2024-video">
<titleInfo>
<title>Video Discourse Parsing and Its Application to Multimodal Summarization: A Dataset and Baseline Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsutomu</namePart>
<namePart type="family">Hirao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manabu</namePart>
<namePart type="family">Okumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akisato</namePart>
<namePart type="family">Kimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper tackles a new task: discourse parsing for videos, inspired by text discourse parsing based on Rhetorical Structure Theory (RST). The task aims to construct an RST tree for a video to represent its storyline and illustrate the event relationships. We first construct a benchmark dataset by identifying events with their time spans, providing corresponding captions, and constructing RST trees with events as leaves. We then evaluate baseline approaches to video RST parsing: the ‘parsing after captioning’ framework and parsing via visual features. The results show that a parser using gold captions performed the best, while parsers relying on generated captions performed the worst; a parser using visual features provided intermediate performance. However, we observed that parsing via visual features could be improved by pre-training it with video captioning designed to produce a coherent video story. Furthermore, we demonstrated that RST trees obtained from videos contribute to multimodal summarization consisting of keyframes with texts.</abstract>
<identifier type="citekey">hirao-etal-2024-video</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.581</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.581/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>9943</start>
<end>9958</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video Discourse Parsing and Its Application to Multimodal Summarization: A Dataset and Baseline Approaches
%A Hirao, Tsutomu
%A Kobayashi, Naoki
%A Kamigaito, Hidetaka
%A Okumura, Manabu
%A Kimura, Akisato
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F hirao-etal-2024-video
%X This paper tackles a new task: discourse parsing for videos, inspired by text discourse parsing based on Rhetorical Structure Theory (RST). The task aims to construct an RST tree for a video to represent its storyline and illustrate the event relationships. We first construct a benchmark dataset by identifying events with their time spans, providing corresponding captions, and constructing RST trees with events as leaves. We then evaluate baseline approaches to video RST parsing: the ‘parsing after captioning’ framework and parsing via visual features. The results show that a parser using gold captions performed the best, while parsers relying on generated captions performed the worst; a parser using visual features provided intermediate performance. However, we observed that parsing via visual features could be improved by pre-training it with video captioning designed to produce a coherent video story. Furthermore, we demonstrated that RST trees obtained from videos contribute to multimodal summarization consisting of keyframes with texts.
%R 10.18653/v1/2024.findings-emnlp.581
%U https://aclanthology.org/2024.findings-emnlp.581/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.581
%P 9943-9958
Markdown (Informal)
[Video Discourse Parsing and Its Application to Multimodal Summarization: A Dataset and Baseline Approaches](https://aclanthology.org/2024.findings-emnlp.581/) (Hirao et al., Findings 2024)
ACL