Towards Inter-character Relationship-driven Story Generation
This work addresses the challenge of generating coherent stories with specific character relationships, which is an incremental improvement in narrative AI for applications like creative writing or interactive storytelling.
The paper tackles the problem of modeling interpersonal relationships for story generation by proposing ReLiSt, a method that uses latent variables to select and express relationships sentence by sentence, resulting in stories that are more faithful to desired relationships while maintaining content quality.
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.