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.
BibTeX
@inproceedings{hsu-etal-2021-scicap-generating,
title = "{S}ci{C}ap: Generating Captions for Scientific Figures",
author = "Hsu, Ting-Yao and
Giles, C Lee and
Huang, Ting-Hao",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.277/",
doi = "10.18653/v1/2021.findings-emnlp.277",
pages = "3258--3264"
}