@inproceedings{huang-etal-2023-summaries,
title = "Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization",
author = "Huang, Chieh-Yang and
Hsu, Ting-Yao and
Rossi, Ryan and
Nenkova, Ani and
Kim, Sungchul and
Chan, Gromit Yeuk-Yin and
Koh, Eunyee and
Giles, C Lee and
Huang, Ting-Hao",
editor = "Keet, C. Maria and
Lee, Hung-Yi and
Zarrie{\ss}, Sina",
booktitle = "Proceedings of the 16th International Natural Language Generation Conference",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.inlg-main.6",
doi = "10.18653/v1/2023.inlg-main.6",
pages = "80--92",
abstract = "Good figure captions help paper readers understand complex scientific figures. Unfortunately, even published papers often have poorly written captions. Automatic caption generation could aid paper writers by providing good starting captions that can be refined for better quality. Prior work often treated figure caption generation as a vision-to-language task. In this paper, we show that it can be more effectively tackled as a text summarization task in scientific documents. We fine-tuned PEGASUS, a pre-trained abstractive summarization model, to specifically summarize figure-referencing paragraphs (e.g., {``}Figure 3 shows...{''}) into figure captions. Experiments on large-scale arXiv figures show that our method outperforms prior vision methods in both automatic and human evaluations. We further conducted an in-depth investigation focused on two key challenges: (i) the common presence of low-quality author-written captions and (ii) the lack of clear standards for good captions. Our code and data are available at: https://github.com/Crowd-AI-Lab/Generating-Figure-Captions-as-a-Text-Summarization-Task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2023-summaries">
<titleInfo>
<title>Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization</title>
</titleInfo>
<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">Ting-Yao</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ani</namePart>
<namePart type="family">Nenkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungchul</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gromit</namePart>
<namePart type="given">Yeuk-Yin</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunyee</namePart>
<namePart type="family">Koh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Giles</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>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Keet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Good figure captions help paper readers understand complex scientific figures. Unfortunately, even published papers often have poorly written captions. Automatic caption generation could aid paper writers by providing good starting captions that can be refined for better quality. Prior work often treated figure caption generation as a vision-to-language task. In this paper, we show that it can be more effectively tackled as a text summarization task in scientific documents. We fine-tuned PEGASUS, a pre-trained abstractive summarization model, to specifically summarize figure-referencing paragraphs (e.g., “Figure 3 shows...”) into figure captions. Experiments on large-scale arXiv figures show that our method outperforms prior vision methods in both automatic and human evaluations. We further conducted an in-depth investigation focused on two key challenges: (i) the common presence of low-quality author-written captions and (ii) the lack of clear standards for good captions. Our code and data are available at: https://github.com/Crowd-AI-Lab/Generating-Figure-Captions-as-a-Text-Summarization-Task.</abstract>
<identifier type="citekey">huang-etal-2023-summaries</identifier>
<identifier type="doi">10.18653/v1/2023.inlg-main.6</identifier>
<location>
<url>https://aclanthology.org/2023.inlg-main.6</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>80</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
%A Huang, Chieh-Yang
%A Hsu, Ting-Yao
%A Rossi, Ryan
%A Nenkova, Ani
%A Kim, Sungchul
%A Chan, Gromit Yeuk-Yin
%A Koh, Eunyee
%A Giles, C. Lee
%A Huang, Ting-Hao
%Y Keet, C. Maria
%Y Lee, Hung-Yi
%Y Zarrieß, Sina
%S Proceedings of the 16th International Natural Language Generation Conference
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F huang-etal-2023-summaries
%X Good figure captions help paper readers understand complex scientific figures. Unfortunately, even published papers often have poorly written captions. Automatic caption generation could aid paper writers by providing good starting captions that can be refined for better quality. Prior work often treated figure caption generation as a vision-to-language task. In this paper, we show that it can be more effectively tackled as a text summarization task in scientific documents. We fine-tuned PEGASUS, a pre-trained abstractive summarization model, to specifically summarize figure-referencing paragraphs (e.g., “Figure 3 shows...”) into figure captions. Experiments on large-scale arXiv figures show that our method outperforms prior vision methods in both automatic and human evaluations. We further conducted an in-depth investigation focused on two key challenges: (i) the common presence of low-quality author-written captions and (ii) the lack of clear standards for good captions. Our code and data are available at: https://github.com/Crowd-AI-Lab/Generating-Figure-Captions-as-a-Text-Summarization-Task.
%R 10.18653/v1/2023.inlg-main.6
%U https://aclanthology.org/2023.inlg-main.6
%U https://doi.org/10.18653/v1/2023.inlg-main.6
%P 80-92
Markdown (Informal)
[Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization](https://aclanthology.org/2023.inlg-main.6) (Huang et al., INLG-SIGDIAL 2023)
ACL
- Chieh-Yang Huang, Ting-Yao Hsu, Ryan Rossi, Ani Nenkova, Sungchul Kim, Gromit Yeuk-Yin Chan, Eunyee Koh, C Lee Giles, and Ting-Hao Huang. 2023. Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization. In Proceedings of the 16th International Natural Language Generation Conference, pages 80–92, Prague, Czechia. Association for Computational Linguistics.