Abstract
Crafting effective captions for figures is important. Readers heavily depend on these captions to grasp the figure's message. However, despite a well-developed set of AI technologies for figures and captions, these have rarely been tested for usefulness in aiding caption writing. This paper introduces SciCapenter, an interactive system that puts together cutting-edge AI technologies for scientific figure captions to aid caption composition. SciCapenter generates a variety of captions for each figure in a scholarly article, providing scores and a comprehensive checklist to assess caption quality across multiple critical aspects, such as helpfulness, OCR mention, key takeaways, and visual properties reference. Users can directly edit captions in SciCapenter, resubmit for revised evaluations, and iteratively refine them. A user study with Ph.D. students indicates that SciCapenter significantly lowers the cognitive load of caption writing. Participants' feedback further offers valuable design insights for future systems aiming to enhance caption writing.
Abstract (translated)
制作有效的图例是重要的。读者 heavily依赖这些图例来理解图中的信息。然而,尽管为图和图例开发了一套先进的AI技术,但这些技术很少被测试其对帮助编写的有用性。本文介绍了SciCapenter,一个交互式系统,旨在结合最先进的AI技术,帮助科学图例的编写。SciCapenter为每张图生成多种图例,提供分数和全面的审核清单,以评估图例在多个关键方面的质量,如有用性、OCR提及、关键要点和视觉特性参考。用户可以直接在SciCapenter中编辑图例,重新提交进行修订,并逐步改进它们。一份用户研究结果表明,SciCapenter显著降低了编写图例的认知负担。参与者的反馈进一步提供了有价值的系统设计洞察,为未来的系统旨在增强编写图例提供了指导。
URL
https://arxiv.org/abs/2403.17784