@inproceedings{hsu-etal-2019-visual,
title = "Visual Story Post-Editing",
author = "Hsu, Ting-Yao and
Huang, Chieh-Yang and
Hsu, Yen-Chia and
Huang, Ting-Hao",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1658",
doi = "10.18653/v1/P19-1658",
pages = "6581--6586",
abstract = "We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task. The dataset ,VIST-Edit, includes 14,905 human-edited versions of 2,981 machine-generated visual stories. The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions. We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models. We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsu-etal-2019-visual">
<titleInfo>
<title>Visual Story Post-Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting-Yao</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chieh-Yang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yen-Chia</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting-Hao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task. The dataset ,VIST-Edit, includes 14,905 human-edited versions of 2,981 machine-generated visual stories. The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions. We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models. We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics.</abstract>
<identifier type="citekey">hsu-etal-2019-visual</identifier>
<identifier type="doi">10.18653/v1/P19-1658</identifier>
<location>
<url>https://aclanthology.org/P19-1658</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>6581</start>
<end>6586</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Story Post-Editing
%A Hsu, Ting-Yao
%A Huang, Chieh-Yang
%A Hsu, Yen-Chia
%A Huang, Ting-Hao
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F hsu-etal-2019-visual
%X We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task. The dataset ,VIST-Edit, includes 14,905 human-edited versions of 2,981 machine-generated visual stories. The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions. We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models. We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics.
%R 10.18653/v1/P19-1658
%U https://aclanthology.org/P19-1658
%U https://doi.org/10.18653/v1/P19-1658
%P 6581-6586
Markdown (Informal)
[Visual Story Post-Editing](https://aclanthology.org/P19-1658) (Hsu et al., ACL 2019)
ACL
- Ting-Yao Hsu, Chieh-Yang Huang, Yen-Chia Hsu, and Ting-Hao Huang. 2019. Visual Story Post-Editing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6581–6586, Florence, Italy. Association for Computational Linguistics.