{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/d2s-document-to-slide-generation-via-query","title":"D2S: Document-to-Slide Generation Via Query-Based Text Summarization","arxiv_id":"2105.03664","date":"2021-05-08","proceeding":"NAACL 2021 4","authors":["Edward Sun","Yufang Hou","Dakuo Wang","Yunfeng Zhang","Nancy X. R. Wang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2105.03664v1","url_pdf":"https://arxiv.org/pdf/2105.03664v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"d2s-document-to-slide-generation-via-query","repo_url":"https://github.com/IBM/document2slides","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"long-form-question-answering","task_name":"Long Form Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[{"slug":"sciduet","name":"SciDuet","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.03664","atlas_url":"https://app.syntology.ai/?focus=2105.03664","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}