PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking

TL;DR

This paper introduces PlotMachines, a neural model for outline-conditioned story generation that tracks dynamic plot states and incorporates discourse structure to produce coherent narratives aligned with key plot points.

Contribution

The paper presents a novel neural model that effectively tracks dynamic plot states and integrates discourse structure for improved outline-conditioned story generation.

Findings

Large-scale models struggle with coherence in outline-based stories.

Dynamic plot state tracking improves narrative consistency.

Discourse structure enhances writing style adaptation.

Abstract

We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline. This task is challenging as the input only provides a rough sketch of the plot, and thus, models need to generate a story by interweaving the key points provided in the outline. This requires the model to keep track of the dynamic states of the latent plot, conditioning on the input outline while generating the full story. We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative. Comprehensive experiments over three fiction and non-fiction datasets demonstrate that large-scale language models, such as GPT-2 and Grover, despite their impressive generation performance, are not sufficient in generating coherent narratives for the given outline, and dynamic plot state tracking is important for composing narratives with tighter, more consistent plots.