Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization

Chieh-Yang Huang, Ting-Yao Hsu, Ryan Rossi, Ani Nenkova, Sungchul Kim, Gromit Yeuk-Yin Chan, Eunyee Koh, C Lee Giles, Ting-Hao Huang


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.
Anthology ID:
2023.inlg-main.6
Volume:
Proceedings of the 16th International Natural Language Generation Conference
Month:
September
Year:
2023
Address:
Prague, Czechia
Editors:
C. Maria Keet, Hung-Yi Lee, Sina Zarrieß
Venues:
INLG | SIGDIAL
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
80–92
Language:
URL:
https://aclanthology.org/2023.inlg-main.6
DOI:
10.18653/v1/2023.inlg-main.6
Bibkey:
Cite (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.
Cite (Informal):
Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization (Huang et al., INLG-SIGDIAL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.inlg-main.6.pdf
Supplementary attachment:
 2023.inlg-main.6.Supplementary_Attachment.pdf