mlsanityData to 14 Oct 2026

D2S: Document-to-Slide Generation Via Query-Based Text Summarization

arXiv 2105.03664 ↗First posted 8 May 2021cs.CLcited by 50

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). Builds on 21 of its 48 references that are in the map. First posted on arXiv 8 May 2021.

Builds on

21 of 48 references.

References · 21

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  6. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  7. 2015Teaching Machines to Read and Comprehendcited by 1,049
  8. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  9. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  10. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  11. 2019ELI5: Long Form Question Answeringcited by 575
  12. 2019Text Summarization with Pretrained Encoderscited by 556
9 more
  1. 2018Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategiescited by 294
  2. 2019Neural Text Summarization: A Critical Evaluationcited by 189
  3. 2018Bottom-Up Abstractive Summarizationcited by 177
  4. 2020TLDR: Extreme Summarization of Scientific Documentscited by 136
  5. 2019Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Constructioncited by 50
  6. 2021How AI Developers Overcome Communication Challenges in a Multidisciplinary Team: A Case Studycited by 29
  7. 2019A Summarization System for Scientific Documentscited by 17
  8. 2019Automatically Generating Engaging Presentation Slide Deckscited by 9
  9. 2021CASS: Towards Building a Social-Support Chatbot for Online Health Communitycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 7; 2025: 15; 2026: 20.

50 papers.

Sort:

By area:

  1. 2024MuirBench: A Comprehensive Benchmark for Robust Multi-image Understandingcited by 188
  2. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 179
  3. 2025PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slidescited by 86
  4. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 85
  5. 2022An Empirical Survey on Long Document Summarization: Datasets, Models and Metricscited by 74
  6. 2025AutoPresent: Designing Structured Visuals from Scratchcited by 68
  7. 2025Paper2Poster: Towards Multimodal Poster Automation from Scientific Paperscited by 63
  8. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 42
  9. 2022GEMv2: Multilingual NLG Benchmarking in a Single Line of Codecited by 36
  10. 2025Paper2Video: Automatic Video Generation from Scientific Paperscited by 24
  11. 2022CiteBench: A benchmark for Scientific Citation Text Generationcited by 22
  12. 2026DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generationcited by 18
38 more
  1. 2024Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approachcited by 17
  2. 2025PreGenie: An Agentic Framework for High-quality Visual Presentation Generationcited by 16
  3. 2022Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Workcited by 15
  4. 2024SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinementcited by 15
  5. 2025SlideTailor: Personalized Presentation Slide Generation for Scientific Paperscited by 13
  6. 2026DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editingcited by 11
  7. 2024Presentations are not always linear! GNN meets LLM for Document-to-Presentation Transformation with Attributioncited by 10
  8. 2023Improving Biomedical Abstractive Summarisation with Knowledge Aggregation from Citation Paperscited by 9
  9. 2025PASS: Presentation Automation for Slide Generation and Speechcited by 7
  10. 2024Knowledge-Centric Templatic Views of Documentscited by 5
  11. 2024Bridging Research and Readers: A Multi-Modal Automated Academic Papers Interpretation Systemcited by 5
  12. 2024PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimizationcited by 5
  13. 2026Any2Poster: Any-Source Poster Generation Across Modalities and Domainscited by 5
  14. 2025Textual-to-Visual Iterative Self-Verification for Slide Generationcited by 4
  15. 2025Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documentscited by 3
  16. 2025VideoAgent: Personalized Synthesis of Scientific Videoscited by 3
  17. 2025SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understandingcited by 3
  18. 2026Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generationcited by 3
  19. 2025Taming LLMs with Negative Samples: A Reference-Free Framework to Evaluate Presentation Content with Actionable Feedbackcited by 2
  20. 2026Demo2Tutorial: From Human Experience to Multimodal Software Tutorialscited by 2
  21. 2026ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blogcited by 2
  22. 2025Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesiscited by 1
  23. 2025DesignLab: Designing Slides Through Iterative Detection and Correctioncited by 1
  24. 2026CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancementcited by 1
  25. 2026Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Mediacited by 1
  26. 2026MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revisioncited by 1
  27. 2026PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputscited by 1
  28. 2026SeaSlides: Semantic Abstraction Layer for Agentic Slide Generationcited by 1
  29. 2026PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slidescited by 1
  30. 2023'Don't Get Too Technical with Me': A Discourse Structure-Based Framework for Science Journalismcited by 0
  31. 2026Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figurescited by 0
  32. 2026A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talkscited by 0
  33. 2026Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoisingcited by 0
  34. 2026ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generationcited by 0
  35. 2026ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedbackcited by 0
  36. 2026SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifactscited by 0
  37. 2026From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contractscited by 0
  38. 2026SlideLab: Audience-Centered Scientific Slide Generation and Evaluationcited by 0