Strategies for Structuring Story Generation

ACL 2019

Strategies for Structuring Story Generation

Jan 30, 2021
|
25 views
|
Details
Abstract: Writers often 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. Authors: Angela Fan, Mike Lewis, Yann Dauphin (FAIR, Google AI)

Comments
loading...