Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
This addresses the issue of poorly written captions in scientific papers, aiding paper writers by providing automated starting captions, though it is incremental as it adapts existing summarization models to a specific domain.
The paper tackled the problem of generating figure captions for scientific documents by treating it as a text summarization task instead of a vision-to-language task, and their method outperformed prior vision-based approaches in both automatic and human evaluations on large-scale arXiv figures.
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.