Research map / Large language models / Language, safety and interpretability
Story Realization: Expanding Plot Events into Sentences
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 |
|---|---|---|---|
| Replace standard beam-search seq2seq with the full ensemble | Event-to-sentence generation · Sci-fi test set | BLEU-4: 0.040 -> 0.0481 | Helped |
| Replace standard beam-search seq2seq with the full ensemble | Event-to-sentence generation · Sci-fi test set | Perplexity: 83.410 -> 70.179 | Helped |
| Add the FSM model to the RetEdit+Templates+Monte Carlo combination (ablation) | Event-to-sentence ensemble · Sci-fi test set | BLEU-4: 0.0462 -> 0.0481 | Helped |
| Add the FSM model to the RetEdit+Templates+Monte Carlo combination (ablation) | Event-to-sentence ensemble · Sci-fi test set | Perplexity: 73.637 -> 70.179 | Helped |
| Add Templates and FSM to RetEdit+Monte Carlo (ablation) | Event-to-sentence ensemble · Sci-fi test set | BLEU-4: 0.0468 -> 0.0481 | Helped |
| Add Templates and FSM to RetEdit+Monte Carlo (ablation) | Event-to-sentence ensemble · Sci-fi test set | Perplexity: 72.441 -> 70.179 | Helped |
| Add RetEdit and FSM to Templates+Monte Carlo (ablation) | Event-to-sentence ensemble · Sci-fi test set | BLEU-4: 0.0409 -> 0.0481 | Helped |
| Add RetEdit and FSM to Templates+Monte Carlo (ablation) | Event-to-sentence ensemble · Sci-fi test set | Perplexity: 79.295 -> 70.179 | Helped |
| Add RetEdit and Monte Carlo to Templates+FSM (ablation) | Event-to-sentence ensemble · Sci-fi test set | BLEU-4: 0.0296 -> 0.0481 | Helped |
| Add RetEdit and Monte Carlo to Templates+FSM (ablation) | Event-to-sentence ensemble · Sci-fi test set | Perplexity: 79.238 -> 70.179 | Helped |
| Use Monte Carlo decoding rather than standard seq2seq decoding | Event-to-sentence model · Sci-fi test set | BLEU-4: 0.040 -> 0.0453 | Helped |
| Use sentence templating rather than standard seq2seq decoding | Event-to-sentence model · Sci-fi test set | BLEU-4: 0.040 -> 0.0034 | Hurt |
Closest papers by meaning
- Event Representations for Automated Story Generation with Deep Neural Nets (AAAI 2018 · similarity 0.93)
- Plan-and-Write: Towards Better Automatic Storytelling (AAAI 2019 · similarity 0.89)
- A Character-Centric Neural Model for Automated Story Generation (AAAI 2020 · similarity 0.88)
- What Happens Next? Event Prediction Using a Compositional Neural Network Model (AAAI 2016 · similarity 0.87)
- Narrative Plan Generation with Self-Supervised Learning (AAAI 2021 · similarity 0.87)
- A Generative Approach for Script Event Prediction via Contrastive Fine-Tuning (AAAI 2023 · similarity 0.86)
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.