@inproceedings{liu-etal-2020-multistage,
title = "Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos",
author = "Liu, Nayu and
Sun, Xian and
Yu, Hongfeng and
Zhang, Wenkai and
Xu, Guangluan",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.144",
doi = "10.18653/v1/2020.emnlp-main.144",
pages = "1834--1845",
abstract = "Multimodal summarization for open-domain videos is an emerging task, aiming to generate a summary from multisource information (video, audio, transcript). Despite the success of recent multiencoder-decoder frameworks on this task, existing methods lack fine-grained multimodality interactions of multisource inputs. Besides, unlike other multimodal tasks, this task has longer multimodal sequences with more redundancy and noise. To address these two issues, we propose a multistage fusion network with the fusion forget gate module, which builds upon this approach by modeling fine-grained interactions between the modalities through a multistep fusion schema and controlling the flow of redundant information between multimodal long sequences via a forgetting module. Experimental results on the How2 dataset show that our proposed model achieves a new state-of-the-art performance. Comprehensive analysis empirically verifies the effectiveness of our fusion schema and forgetting module on multiple encoder-decoder architectures. Specially, when using high noise ASR transcripts (WER{\textgreater}30{\%}), our model still achieves performance close to the ground-truth transcript model, which reduces manual annotation cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2020-multistage">
<titleInfo>
<title>Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nayu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfeng</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenkai</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangluan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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 for open-domain videos is an emerging task, aiming to generate a summary from multisource information (video, audio, transcript). Despite the success of recent multiencoder-decoder frameworks on this task, existing methods lack fine-grained multimodality interactions of multisource inputs. Besides, unlike other multimodal tasks, this task has longer multimodal sequences with more redundancy and noise. To address these two issues, we propose a multistage fusion network with the fusion forget gate module, which builds upon this approach by modeling fine-grained interactions between the modalities through a multistep fusion schema and controlling the flow of redundant information between multimodal long sequences via a forgetting module. Experimental results on the How2 dataset show that our proposed model achieves a new state-of-the-art performance. Comprehensive analysis empirically verifies the effectiveness of our fusion schema and forgetting module on multiple encoder-decoder architectures. Specially, when using high noise ASR transcripts (WER\textgreater30%), our model still achieves performance close to the ground-truth transcript model, which reduces manual annotation cost.</abstract>
<identifier type="citekey">liu-etal-2020-multistage</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.144</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.144</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1834</start>
<end>1845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos
%A Liu, Nayu
%A Sun, Xian
%A Yu, Hongfeng
%A Zhang, Wenkai
%A Xu, Guangluan
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F liu-etal-2020-multistage
%X Multimodal summarization for open-domain videos is an emerging task, aiming to generate a summary from multisource information (video, audio, transcript). Despite the success of recent multiencoder-decoder frameworks on this task, existing methods lack fine-grained multimodality interactions of multisource inputs. Besides, unlike other multimodal tasks, this task has longer multimodal sequences with more redundancy and noise. To address these two issues, we propose a multistage fusion network with the fusion forget gate module, which builds upon this approach by modeling fine-grained interactions between the modalities through a multistep fusion schema and controlling the flow of redundant information between multimodal long sequences via a forgetting module. Experimental results on the How2 dataset show that our proposed model achieves a new state-of-the-art performance. Comprehensive analysis empirically verifies the effectiveness of our fusion schema and forgetting module on multiple encoder-decoder architectures. Specially, when using high noise ASR transcripts (WER\textgreater30%), our model still achieves performance close to the ground-truth transcript model, which reduces manual annotation cost.
%R 10.18653/v1/2020.emnlp-main.144
%U https://aclanthology.org/2020.emnlp-main.144
%U https://doi.org/10.18653/v1/2020.emnlp-main.144
%P 1834-1845
Markdown (Informal)
[Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos](https://aclanthology.org/2020.emnlp-main.144) (Liu et al., EMNLP 2020)
ACL