Research map / Label-efficient and robust learning / Self-supervised and contrastive
Narrative Plan Generation with Self-Supervised 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 the encoder-decoder AE rather than LSTM without an encoder (ablation) | Narrative plan generation · Medical | generative factor: 0.84 (0.26) -> 2.14 (0.73); 0.38 (0.19) -> 1.94 (0.28); 0.17 (0.08) -> 1.57 (0.28) | Helped |
| Use the encoder-decoder AE rather than LSTM without an encoder (ablation) | Narrative plan generation · Western | generative factor: 0.06 (0.14) -> 0.21 (0.17); 0.01 (0.01) -> 0.23 (0.24); 0.11 (0.25) -> 0.25 (0.25) | Helped |
| Use the encoder-decoder AE rather than LSTM without an encoder (ablation) | Narrative plan generation · Aladdin | generative factor: 3.78 (0.59) -> 3.46 (0.40); 1.02 (0.14) -> 1.56 (0.59); 0.44 (0.09) -> 0.91 (0.29) | Mixed |
| Use the encoder-decoder AE rather than LSTM without an encoder (ablation) | Narrative plan generation · Red | generative factor: 3.10 (0.60) -> 2.18 (0.26); 1.21 (0.36) -> 1.38 (0.23); 0.71 (0.14) -> 0.93 (0.25) | Mixed |
| Replace the AE sampling approach with VAE | Narrative plan generation · Aladdin | generative factor: 3.46 (0.40) vs 3.39 (1.06); 1.56 (0.59) vs 1.63 (0.36); 0.91 (0.29) vs 0.94 (0.36) | Mixed |
| Replace the AE sampling approach with VAE | Narrative plan generation · Medical | generative factor: 2.14 (0.73) vs 2.43 (1.74); 1.94 (0.28) vs 1.55 (0.94); 1.57 (0.28) vs 0.96 (0.48) | Mixed |
| Replace the AE sampling approach with VAE | Narrative plan generation · Red | generative factor: 2.18 (0.26) vs 1.04 (0.37); 1.38 (0.23) vs 0.66 (0.16); 0.93 (0.25) vs 0.45 (0.15) | Helped |
| Replace the AE sampling approach with VAE | Narrative plan generation · Western | generative factor: 0.21 (0.17) vs <0.01; 0.23 (0.24) vs <0.01; 0.25 (0.25) vs <0.01 | Helped |
| Increase the training set size | AE narrative plan generation · Aladdin | generative factor: 3.46 (0.40) -> 1.56 (0.59) -> 0.91 (0.29) | Hurt |
| Increase the training set size | AE narrative plan generation · Medical | generative factor: 2.14 (0.73) -> 1.94 (0.28) -> 1.57 (0.28) | Hurt |
| Increase the training set size | AE narrative plan generation · Red | generative factor: 2.18 (0.26) -> 1.38 (0.23) -> 0.93 (0.25) | Hurt |
| Increase the training set size | AE narrative plan generation · Western | generative factor: 0.21 (0.17) -> 0.23 (0.24) -> 0.25 (0.25) | Helped |
Closest papers by meaning
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.86)
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency (NeurIPS 2025 · similarity 0.86)
- NaRuto: Automatically Acquiring Planning Models from Narrative Texts (AAAI 2024 · similarity 0.85)
- Does Robin Hood Use a Lightsaber?: Automated Planning for Storytelling (AAAI 2024 · similarity 0.85)
- VinaBench: Benchmark for Faithful and Consistent Visual Narratives (CVPR 2025 · similarity 0.84)
- Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning (CVPR 2026 · similarity 0.84)
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.