@inproceedings{li-etal-2020-multimodal,
title = "Multimodal Sentence Summarization via Multimodal Selective Encoding",
author = "Li, Haoran and
Zhu, Junnan and
Zhang, Jiajun and
He, Xiaodong and
Zong, Chengqing",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.496/",
doi = "10.18653/v1/2020.coling-main.496",
pages = "5655--5667",
abstract = "This paper studies the problem of generating a summary for a given sentence-image pair. Existing multimodal sequence-to-sequence approaches mainly focus on enhancing the decoder by visual signals, while ignoring that the image can improve the ability of the encoder to identify highlights of a news event or a document. Thus, we propose a multimodal selective gate network that considers reciprocal relationships between textual and multi-level visual features, including global image descriptor, activation grids, and object proposals, to select highlights of the event when encoding the source sentence. In addition, we introduce a modality regularization to encourage the summary to capture the highlights embedded in the image more accurately. To verify the generalization of our model, we adopt the multimodal selective gate to the text-based decoder and multimodal-based decoder. Experimental results on a public multimodal sentence summarization dataset demonstrate the advantage of our models over baselines. Further analysis suggests that our proposed multimodal selective gate network can effectively select important information in the input sentence."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-multimodal">
<titleInfo>
<title>Multimodal Sentence Summarization via Multimodal Selective Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper studies the problem of generating a summary for a given sentence-image pair. Existing multimodal sequence-to-sequence approaches mainly focus on enhancing the decoder by visual signals, while ignoring that the image can improve the ability of the encoder to identify highlights of a news event or a document. Thus, we propose a multimodal selective gate network that considers reciprocal relationships between textual and multi-level visual features, including global image descriptor, activation grids, and object proposals, to select highlights of the event when encoding the source sentence. In addition, we introduce a modality regularization to encourage the summary to capture the highlights embedded in the image more accurately. To verify the generalization of our model, we adopt the multimodal selective gate to the text-based decoder and multimodal-based decoder. Experimental results on a public multimodal sentence summarization dataset demonstrate the advantage of our models over baselines. Further analysis suggests that our proposed multimodal selective gate network can effectively select important information in the input sentence.</abstract>
<identifier type="citekey">li-etal-2020-multimodal</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.496</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.496/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5655</start>
<end>5667</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Sentence Summarization via Multimodal Selective Encoding
%A Li, Haoran
%A Zhu, Junnan
%A Zhang, Jiajun
%A He, Xiaodong
%A Zong, Chengqing
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F li-etal-2020-multimodal
%X This paper studies the problem of generating a summary for a given sentence-image pair. Existing multimodal sequence-to-sequence approaches mainly focus on enhancing the decoder by visual signals, while ignoring that the image can improve the ability of the encoder to identify highlights of a news event or a document. Thus, we propose a multimodal selective gate network that considers reciprocal relationships between textual and multi-level visual features, including global image descriptor, activation grids, and object proposals, to select highlights of the event when encoding the source sentence. In addition, we introduce a modality regularization to encourage the summary to capture the highlights embedded in the image more accurately. To verify the generalization of our model, we adopt the multimodal selective gate to the text-based decoder and multimodal-based decoder. Experimental results on a public multimodal sentence summarization dataset demonstrate the advantage of our models over baselines. Further analysis suggests that our proposed multimodal selective gate network can effectively select important information in the input sentence.
%R 10.18653/v1/2020.coling-main.496
%U https://aclanthology.org/2020.coling-main.496/
%U https://doi.org/10.18653/v1/2020.coling-main.496
%P 5655-5667
Markdown (Informal)
[Multimodal Sentence Summarization via Multimodal Selective Encoding](https://aclanthology.org/2020.coling-main.496/) (Li et al., COLING 2020)
ACL