Research map / Probabilistic and scientific modeling / Variational and generative sampling
Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder
Meng-Hsuan Yu, Juntao Li, Danyang Liu, Dongyan Zhao, Rui Yan, Bo Tang, Haisong Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace flat decoder with hierarchical decoder in CVAE (ablation) | CVAE · ROCStories | BLEU-1: 25.09 -> 29.41 | Improved |
| replace flat decoder with hierarchical decoder in CVAE (ablation) | CVAE · ROCStories human eval | Consistency: 1.61 -> 2.22 | Improved |
| replace flat decoder with hierarchical decoder in CVAE (ablation) | CVAE · ROCStories | Distinct-2: 17.54 -> 12.33 | Hurt |
| add multi-pass editing to H-CVAE (ablation) | H-CVAE · ROCStories | Distinct-2: 12.33 -> 14.82 | Improved |
| add multi-pass editing to H-CVAE (ablation) | H-CVAE · ROCStories | BLEU-1: 29.41 -> 29.39 | No clear effect |
| add multi-pass editing to H-CVAE (ablation) | H-CVAE · ROCStories human eval | Average score: 2.19 -> 2.22 | Mixed |
| use CVAE instead of seq2seq | S2S · ROCStories | Distinct-2: 2.22 -> 17.54 | Improved |
| use H-CVAE instead of Plan and Write | Plan and Write · ROCStories | BLEU-1: 27.49 -> 29.41 | Mixed |
Closest papers by meaning
- Content Learning with Structure-Aware Writing: A Graph-Infused Dual Conditional Variational Autoencoder for Automatic Storytelling (AAAI 2021 · similarity 0.90)
- Learning to Write Stories with Thematic Consistency and Wording Novelty (AAAI 2019 · similarity 0.89)
- A Character-Centric Neural Model for Automated Story Generation (AAAI 2020 · similarity 0.86)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.83)
- One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt (ICLR 2025 · similarity 0.83)
- CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation (CVPR 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.
