Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts

TL;DR

This paper introduces a novel method for generating stories with flashbacks by using structured event prompts and reinforcement learning, improving temporal coherence and story interest.

Contribution

It proposes a new approach combining event-based temporal prompts with reinforcement learning to enhance flashback generation in stories.

Findings

Generated stories contain more coherent flashbacks.

Stories exhibit increased interest and diversity.

Maintains fluency and temporal consistency.

Abstract

Stories or narratives are comprised of a sequence of events. To compose interesting stories, professional writers often leverage a creative writing technique called flashback that inserts past events into current storylines as we commonly observe in novels and plays. However, it is challenging for machines to generate flashback as it requires a solid understanding of event temporal order (e.g. "feeling hungry" before "eat," not vice versa), and the creativity to arrange storylines so that earlier events do not always appear first in narrative order. Two major issues in existing systems that exacerbate the challenges: 1) temporal bias in pertaining and story datasets that leads to monotonic event temporal orders; 2) lack of explicit guidance that helps machines decide where to insert flashbacks. We propose to address these issues using structured storylines to encode events and their pair-wise temporal relations (before, after and vague) as temporal prompts that guide how stories should unfold temporally. We leverage a Plan-and-Write framework enhanced by reinforcement learning to generate storylines and stories end-to-end. Evaluation results show that the proposed method can generate more interesting stories with flashbacks while maintaining textual diversity, fluency, and temporal coherence.