arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.17784cs.HCcs.AI
收藏

SciCapenter:利用机器生成的标题和评分支持科学图表的标题撰写

SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratings

The Pennsylvania State University(宾夕法尼亚州立大学);Adobe Research(奥多比研究院)

Ting-Yao Hsu, Chieh-Yang Huang, Shih-Hong Huang, Ryan Rossi, Sungchul Kim, Tong Yu, C. Lee Giles, Ting-Hao K. Huang

AI总结:

本文提出交互式系统SciCapenter,整合前沿AI技术为学术图表生成多样化标题并提供多维度质量评分与检查表,支持用户迭代编辑,有效降低了用户撰写标题的认知负荷。

摘要:

为图表撰写有效的标题非常重要。读者严重依赖这些标题来理解图表传达的信息。然而,尽管已有一套成熟的用于图表和标题的 AI 技术,但它们在辅助标题撰写方面的实用性却很少得到测试。本文介绍了 SciCapenter,这是一个交互式系统,它将用于科学图表标题的前沿 AI 技术整合在一起,以辅助标题撰写。SciCapenter 为学术文章中的每个图表生成多种标题,并提供分数和一份全面的检查表,以在多个关键方面评估标题质量,如有用性、OCR 提及、关键要点和视觉属性参考。用户可以在 SciCapenter 中直接编辑标题,重新提交以获取修订后的评估,并对其进行迭代完善。一项针对博士生的用户研究表明,SciCapenter 显著降低了撰写标题的认知负荷。参与者的反馈进一步为未来旨在增强标题撰写的系统提供了宝贵的设计见解。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑