@inproceedings{cheng-etal-2024-event,
title = "Event-Content-Oriented Dialogue Generation in Short Video",
author = "Cheng, Fenghua and
Li, Xue and
Huang, Zi and
Wang, Jinxiang and
Wang, Sen",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.229",
doi = "10.18653/v1/2024.naacl-long.229",
pages = "4114--4124",
abstract = "Understanding complex events from different modalities, associating to external knowledge and generating response in a clear point of view are still unexplored in today{'}s multi-modal dialogue research. The great challenges include 1) lack of event-based multi-modal dialogue dataset; 2) understanding of complex events and 3) heterogeneity gap between different modalities. To overcome these challenges, we firstly introduce a novel event-oriented video-dialogue dataset called SportsVD (Sports-domain Video-dialogue Dataset). To our best knowledge, SportsVD is the first dataset that consists of complex events videos and opinion-based conversations with regards to contents in these events. Meanwhile, we present multi-modal dialogue generation method VCD (Video Commentary Dialogue) to generate human-like response according to event contents in the video and related external knowledge. In contrast to previous video-based dialogue generation, we focus on opinion-based response and the understanding of longer and more complex event contents. We evaluate VCD{'}s performance on SportsVD and other baselines under several automatic metrics. Experiments demonstrate VCD can outperform among other state-of-the-art baselines. Our work is available at https://github.com/Cheng-Fenghua/SportsVD.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2024-event">
<titleInfo>
<title>Event-Content-Oriented Dialogue Generation in Short Video</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fenghua</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinxiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding complex events from different modalities, associating to external knowledge and generating response in a clear point of view are still unexplored in today’s multi-modal dialogue research. The great challenges include 1) lack of event-based multi-modal dialogue dataset; 2) understanding of complex events and 3) heterogeneity gap between different modalities. To overcome these challenges, we firstly introduce a novel event-oriented video-dialogue dataset called SportsVD (Sports-domain Video-dialogue Dataset). To our best knowledge, SportsVD is the first dataset that consists of complex events videos and opinion-based conversations with regards to contents in these events. Meanwhile, we present multi-modal dialogue generation method VCD (Video Commentary Dialogue) to generate human-like response according to event contents in the video and related external knowledge. In contrast to previous video-based dialogue generation, we focus on opinion-based response and the understanding of longer and more complex event contents. We evaluate VCD’s performance on SportsVD and other baselines under several automatic metrics. Experiments demonstrate VCD can outperform among other state-of-the-art baselines. Our work is available at https://github.com/Cheng-Fenghua/SportsVD.</abstract>
<identifier type="citekey">cheng-etal-2024-event</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.229</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.229</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4114</start>
<end>4124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Event-Content-Oriented Dialogue Generation in Short Video
%A Cheng, Fenghua
%A Li, Xue
%A Huang, Zi
%A Wang, Jinxiang
%A Wang, Sen
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F cheng-etal-2024-event
%X Understanding complex events from different modalities, associating to external knowledge and generating response in a clear point of view are still unexplored in today’s multi-modal dialogue research. The great challenges include 1) lack of event-based multi-modal dialogue dataset; 2) understanding of complex events and 3) heterogeneity gap between different modalities. To overcome these challenges, we firstly introduce a novel event-oriented video-dialogue dataset called SportsVD (Sports-domain Video-dialogue Dataset). To our best knowledge, SportsVD is the first dataset that consists of complex events videos and opinion-based conversations with regards to contents in these events. Meanwhile, we present multi-modal dialogue generation method VCD (Video Commentary Dialogue) to generate human-like response according to event contents in the video and related external knowledge. In contrast to previous video-based dialogue generation, we focus on opinion-based response and the understanding of longer and more complex event contents. We evaluate VCD’s performance on SportsVD and other baselines under several automatic metrics. Experiments demonstrate VCD can outperform among other state-of-the-art baselines. Our work is available at https://github.com/Cheng-Fenghua/SportsVD.
%R 10.18653/v1/2024.naacl-long.229
%U https://aclanthology.org/2024.naacl-long.229
%U https://doi.org/10.18653/v1/2024.naacl-long.229
%P 4114-4124
Markdown (Informal)
[Event-Content-Oriented Dialogue Generation in Short Video](https://aclanthology.org/2024.naacl-long.229) (Cheng et al., NAACL 2024)
ACL
- Fenghua Cheng, Xue Li, Zi Huang, Jinxiang Wang, and Sen Wang. 2024. Event-Content-Oriented Dialogue Generation in Short Video. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4114–4124, Mexico City, Mexico. Association for Computational Linguistics.