Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a critical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a two-step approach: 1) Use slide titles to retrieve relevant and engaging text, figures, and tables; 2) Summarize the retrieved context into bullet points with long-form question answering. Our evaluation suggests that long-form QA outperforms state-of-the-art summarization baselines on both automated ROUGE metrics and qualitative human evaluation.

翻译：演示对于我们生活的各个领域的交流至关重要,然而,创建幻灯片甲板往往既乏味又费时,研究范围有限,旨在将文件到幻灯片的生成过程自动化,而且都面临严峻的挑战:没有可供公众查阅的用于培训和基准衡量的数据集。在这项工作中,我们首先提供一个新的数据集,SciDuet,由近年国家实验室和多边实验室会议(如ACL)的双对纸张及其相应的幻灯片甲板组成。第二,我们提出D2S,这是一个处理文件到幻灯片任务的新系统,采用两步方法:1)使用幻灯片标题检索相关和有吸引力的文本、图表和表格;2)将检索到的上下文汇总成长式问题的回答圆点。我们的评价表明,长式QA在自动的ROUGE测量和定性的人评价上都超越了最先进的总和基线。