Content Planning for Neural Story Generation with Aristotelian Rescoring
| Autor: | Ralph Weischedel, Nanyun Peng, Tuhin Chakrabarty, Seraphina Goldfarb-Tarrant |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer Science - Artificial Intelligence business.industry Computer science Narrative text 02 engineering and technology computer.software_genre Cohesion (linguistics) 03 medical and health sciences 0302 clinical medicine Artificial Intelligence (cs.AI) Poetics 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Language model Artificial intelligence business computer Computation and Language (cs.CL) Natural language processing Sentence |
| Zdroj: | EMNLP (1) |
| DOI: | 10.48550/arxiv.2009.09870 |
| Popis: | Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion. We posit that many of the problems of story generation can be addressed via high-quality content planning, and present a system that focuses on how to learn good plot structures to guide story generation. We utilize a plot-generation language model along with an ensemble of rescoring models that each implement an aspect of good story-writing as detailed in Aristotle's Poetics. We find that stories written with our more principled plot-structure are both more relevant to a given prompt and higher quality than baselines that do not content plan, or that plan in an unprincipled way. Comment: EMNLP 2020, 9 pages |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|