Guiding Neural Story Generation with Reader Models
This work addresses the problem of automated storytelling for applications requiring coherent narratives, representing an incremental improvement over existing methods.
The paper tackles the challenge of maintaining coherence and staying on-topic in neural story generation by introducing StoRM, a framework that uses a reader model represented as a knowledge graph to guide narrative progression. Experiments show that StoRM produces significantly more coherent and on-topic stories, outperforming baselines in plot plausibility and topic adherence.
Automated storytelling has long captured the attention of researchers for the ubiquity of narratives in everyday life. However, it is challenging to maintain coherence and stay on-topic toward a specific ending when generating narratives with neural language models. In this paper, we introduce Story generation with Reader Models (StoRM), a framework in which a reader model is used to reason about the story should progress. A reader model infers what a human reader believes about the concepts, entities, and relations about the fictional story world. We show how an explicit reader model represented as a knowledge graph affords story coherence and provides controllability in the form of achieving a given story world state goal. Experiments show that our model produces significantly more coherent and on-topic stories, outperforming baselines in dimensions including plot plausibility and staying on topic.