Research map / Large language models / Agents, code and math
Narrative Planning Model Acquisition from Text Summaries and Descriptions
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 sieve Algorithm 1 instead of CoreNLP | Algorithm 1 · House synopsis | % pronouns correctly resolved: 16.4% -> 92.7% | Helped |
| use sieve Algorithm 1 instead of spaCy | Algorithm 1 · House synopsis | % pronouns correctly resolved: 32.7% -> 92.7% | Helped |
| use sieve Algorithm 1 instead of CoreNLP | Algorithm 1 · Scooby Doo synopsis | % pronouns correctly resolved: 38% -> 81% | Helped |
| use sieve Algorithm 1 instead of spaCy | Algorithm 1 · Scooby Doo synopsis | % pronouns correctly resolved: 32% -> 81% | Helped |
| use sieve Algorithm 1 instead of CoreNLP | Algorithm 1 · Lord of the Flies synopsis | % pronouns correctly resolved: 62.7% -> 88.2% | Helped |
| use sieve Algorithm 1 instead of spaCy | Algorithm 1 · Christmas Carol synopsis | % pronouns correctly resolved: 76.9% -> 80.8% | Helped |
| use sieve Algorithm 1 instead of CoreNLP | Algorithm 1 · Christmas Carol synopsis | % pronouns correctly resolved: 53.8% -> 80.8% | Helped |
| use sieve Algorithm 1 instead of spaCy | Algorithm 1 · Friends synopsis | % pronouns correctly resolved: 60% -> 80% | Helped |
| use sieve Algorithm 1 instead of CoreNLP | Algorithm 1 · Toy Story synopsis | % pronouns correctly resolved: 40.0% -> 62.5% | Helped |
| semi-automated user edits (delete, merge, change) to the automated House domain model | Automated model · House | number of actions in output plan: 69 -> 45 | Helped |
| semi-automated user edits to the automated Jungle Book domain model | Automated model · Jungle Book | number of actions in output plan: 83 -> 58 | Helped |
| automated model versus hand-crafted model | Automated model · House | number of actions in output plan: 9 -> 69 | Mixed |
Closest papers by meaning
- NaRuto: Automatically Acquiring Planning Models from Narrative Texts (AAAI 2024 · similarity 0.89)
- Does Robin Hood Use a Lightsaber?: Automated Planning for Storytelling (AAAI 2024 · similarity 0.86)
- Large Language Models as Planning Domain Generators (Student Abstract) (AAAI 2024 · similarity 0.85)
- NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing (AAAI 2024 · similarity 0.85)
- Planning in the Dark: LLM-Symbolic Planning Pipeline Without Experts (AAAI 2025 · similarity 0.84)
- Agents' Room: Narrative Generation through Multi-step Collaboration (ICLR 2025 · similarity 0.83)
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.