Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Topic-Aware Slide Generation For Academic Papers With Unsupervised Mutual Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use topic-aware mutual learning with neural and log-linear sentence extractors | academic paper slide sentence selection · Contribution | accuracy: 0.87; Rule@section 0.95 | Mixed |
| use topic-aware mutual learning with neural and log-linear sentence extractors | academic paper slide sentence selection · Dataset | accuracy: 0.44; BERT QA (sent3) 0.48 | No clear effect |
| use topic-aware mutual learning with neural and log-linear sentence extractors | academic paper slide sentence selection · Baseline | accuracy: 0.31; Rule@section 0.41 | Hurt |
| use topic-aware mutual learning with neural and log-linear sentence extractors | academic paper slide sentence selection · Future Work | accuracy: 0.72; BERT QA (sent3) 0.55 | Helped |
| include all keyword, BERT-QA, and section priors rather than keyword only (ablation) | neural sentence selector initialization for Future Work · Future Work | accuracy: 0.58 -> 0.63 | Helped |
| include all keyword, BERT-QA, and section priors rather than BERT-QA only (ablation) | neural sentence selector initialization for Future Work · Future Work | accuracy: 0.56 -> 0.63 | Helped |
| include all keyword, BERT-QA, and section priors rather than section only (ablation) | neural sentence selector initialization for Future Work · Future Work | accuracy: 0.16 -> 0.63 | Helped |
| include all keyword, BERT-QA, and section priors rather than keyword only (ablation) | neural sentence selector initialization for Future Work · Future Work | BLEU: 0.61 -> 0.66 | Helped |
| include all keyword, BERT-QA, and section priors rather than BERT-QA only (ablation) | neural sentence selector initialization for Future Work · Future Work | BLEU: 0.61 -> 0.66 | Helped |
| include all keyword, BERT-QA, and section priors rather than section only (ablation) | neural sentence selector initialization for Future Work · Future Work | BLEU: 0.19 -> 0.66 | Helped |
| use model outputs as draft slides | topic-aware slide generation · Human evaluation | overall rating: 3.54 | Helped |
Closest papers by meaning
- Phrase-Based Presentation Slides Generation for Academic Papers (AAAI 2017 · similarity 0.90)
- SlideTailor: Personalized Presentation Slide Generation for Scientific Papers (AAAI 2026 · similarity 0.87)
- AutoPresent: Designing Structured Visuals from Scratch (CVPR 2025 · similarity 0.85)
- Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with Attribution (AAAI 2025 · similarity 0.83)
- PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models (NeurIPS 2024 · similarity 0.83)
- Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.