Towards Inter-character Relationship-driven Story Generation

TL;DR

This paper presents ReLiSt, a novel method for story generation that models interpersonal relationships as latent variables, enabling the creation of more relationship-faithful and interpretable stories.

Contribution

It introduces a new framework, ReLiSt, which incorporates relationship modeling as latent variables to improve story coherence and interpretability.

Findings

ReLiSt generates stories with more faithful relationships.

ReLiSt maintains high content quality.

Relationship assignments enhance interpretability.

Abstract

In this paper, we introduce the task of modeling interpersonal relationships for story generation. For addressing this task, we propose Relationships as Latent Variables for Story Generation, (ReLiSt). ReLiSt generates stories sentence by sentence and has two major components - a relationship selector and a story continuer. The relationship selector specifies a latent variable to pick the relationship to exhibit in the next sentence and the story continuer generates the next sentence while expressing the selected relationship in a coherent way. Our automatic and human evaluations demonstrate that ReLiSt is able to generate stories with relationships that are more faithful to desired relationships while maintaining the content quality. The relationship assignments to sentences during inference bring interpretability to ReLiSt.