SciCap: Generating Captions for Scientific Figures

Ting-Yao Hsu, C Lee Giles, Ting-Hao Huang


Abstract
Researchers use figures to communicate rich, complex information in scientific papers. The captions of these figures are critical to conveying effective messages. However, low-quality figure captions commonly occur in scientific articles and may decrease understanding. In this paper, we propose an end-to-end neural framework to automatically generate informative, high-quality captions for scientific figures. To this end, we introduce SCICAP, a large-scale figure-caption dataset based on computer science arXiv papers published between 2010 and 2020. After pre-processing – including figure-type classification, sub-figure identification, text normalization, and caption text selection – SCICAP contained more than two million figures extracted from over 290,000 papers. We then established baseline models that caption graph plots, the dominant (19.2%) figure type. The experimental results showed both opportunities and steep challenges of generating captions for scientific figures.
Anthology ID:
2021.findings-emnlp.277
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3258–3264
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.277
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.277.pdf
Code
 tingyaohsu/scicap
Data
SCICAPFigureQA