@inproceedings{wang-etal-2020-keep,
title = "Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication",
author = "Wang, Ruize and
Wei, Zhongyu and
Cheng, Ying and
Li, Piji and
Shan, Haijun and
Zhang, Ji and
Zhang, Qi and
Huang, Xuanjing",
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.204/",
doi = "10.18653/v1/2020.coling-main.204",
pages = "2250--2260",
abstract = "Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. In this paper, we propose a new way for visual storytelling by introducing a topic description task to detect the global semantic context of an image stream. A story is then constructed with the guidance of the topic description. In order to combine the two generation tasks, we propose a multi-agent communication framework that regards the topic description generator and the story generator as two agents and learn them simultaneously via iterative updating mechanism. We validate our approach on VIST dataset, where quantitative results, ablations, and human evaluation demonstrate our method`s good ability in generating stories with higher quality compared to state-of-the-art methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2020-keep">
<titleInfo>
<title>Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruize</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piji</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haijun</namePart>
<namePart type="family">Shan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</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>Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. In this paper, we propose a new way for visual storytelling by introducing a topic description task to detect the global semantic context of an image stream. A story is then constructed with the guidance of the topic description. In order to combine the two generation tasks, we propose a multi-agent communication framework that regards the topic description generator and the story generator as two agents and learn them simultaneously via iterative updating mechanism. We validate our approach on VIST dataset, where quantitative results, ablations, and human evaluation demonstrate our method‘s good ability in generating stories with higher quality compared to state-of-the-art methods.</abstract>
<identifier type="citekey">wang-etal-2020-keep</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.204</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.204/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2250</start>
<end>2260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication
%A Wang, Ruize
%A Wei, Zhongyu
%A Cheng, Ying
%A Li, Piji
%A Shan, Haijun
%A Zhang, Ji
%A Zhang, Qi
%A Huang, Xuanjing
%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 wang-etal-2020-keep
%X Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. In this paper, we propose a new way for visual storytelling by introducing a topic description task to detect the global semantic context of an image stream. A story is then constructed with the guidance of the topic description. In order to combine the two generation tasks, we propose a multi-agent communication framework that regards the topic description generator and the story generator as two agents and learn them simultaneously via iterative updating mechanism. We validate our approach on VIST dataset, where quantitative results, ablations, and human evaluation demonstrate our method‘s good ability in generating stories with higher quality compared to state-of-the-art methods.
%R 10.18653/v1/2020.coling-main.204
%U https://aclanthology.org/2020.coling-main.204/
%U https://doi.org/10.18653/v1/2020.coling-main.204
%P 2250-2260
Markdown (Informal)
[Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication](https://aclanthology.org/2020.coling-main.204/) (Wang et al., COLING 2020)
ACL
- Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, and Xuanjing Huang. 2020. Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2250–2260, Barcelona, Spain (Online). International Committee on Computational Linguistics.