Strategies for Structuring Story Generation
This addresses the challenge of structured story generation for writers and AI applications, representing an incremental improvement over existing methods.
The paper tackles the problem of generating long, coherent stories by introducing a coarse-to-fine model that decomposes stories into predicate-argument structures before surface realization, with human judges preferring these stories over previous hierarchical text generation approaches.
Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and introduce new models which decompose stories by abstracting over actions and entities. The model first generates the predicate-argument structure of the text, where different mentions of the same entity are marked with placeholder tokens. It then generates a surface realization of the predicate-argument structure, and finally replaces the entity placeholders with context-sensitive names and references. Human judges prefer the stories from our models to a wide range of previous approaches to hierarchical text generation. Extensive analysis shows that our methods can help improve the diversity and coherence of events and entities in generated stories.