Guiding Neural Story Generation with Reader Models

TL;DR

This paper introduces StoRM, a framework that uses reader models as knowledge graphs to improve the coherence and controllability of neural story generation, leading to more plausible and on-topic narratives.

Contribution

The paper presents a novel reader model-based approach that enhances story coherence and allows goal-directed story generation in neural models.

Findings

Significantly improved story coherence and on-topicness.

Outperforms baselines in plot plausibility.

Enables controllable story generation with specific world state goals.

Abstract

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.