@inproceedings{hong-etal-2023-visual,
title = "Visual Coherence Loss for Coherent and Visually Grounded Story Generation",
author = "Hong, Xudong and
Demberg, Vera and
Sayeed, Asad and
Zheng, Qiankun and
Schiele, Bernt",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.603",
doi = "10.18653/v1/2023.findings-acl.603",
pages = "9456--9470",
abstract = "Local coherence is essential for long-form text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story; (2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for self-supervised learning for image sequence representations. We further propose combining features from an object and a face detector to construct stronger character features. To evaluate input-output relevance that current reference-based metrics don{'}t measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2023-visual">
<titleInfo>
<title>Visual Coherence Loss for Coherent and Visually Grounded Story Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="family">Sayeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiankun</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernt</namePart>
<namePart type="family">Schiele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Local coherence is essential for long-form text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story; (2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for self-supervised learning for image sequence representations. We further propose combining features from an object and a face detector to construct stronger character features. To evaluate input-output relevance that current reference-based metrics don’t measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories.</abstract>
<identifier type="citekey">hong-etal-2023-visual</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.603</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.603</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>9456</start>
<end>9470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Coherence Loss for Coherent and Visually Grounded Story Generation
%A Hong, Xudong
%A Demberg, Vera
%A Sayeed, Asad
%A Zheng, Qiankun
%A Schiele, Bernt
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F hong-etal-2023-visual
%X Local coherence is essential for long-form text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story; (2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for self-supervised learning for image sequence representations. We further propose combining features from an object and a face detector to construct stronger character features. To evaluate input-output relevance that current reference-based metrics don’t measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories.
%R 10.18653/v1/2023.findings-acl.603
%U https://aclanthology.org/2023.findings-acl.603
%U https://doi.org/10.18653/v1/2023.findings-acl.603
%P 9456-9470
Markdown (Informal)
[Visual Coherence Loss for Coherent and Visually Grounded Story Generation](https://aclanthology.org/2023.findings-acl.603) (Hong et al., Findings 2023)
ACL