Controlled Cue Generation for Play Scripts

TL;DR

This paper introduces a new task of generating theatrical cues from dialogues in play scripts, leveraging large-scale data and controlled text generation techniques to enhance dialogue impact.

Contribution

It presents a novel approach to cue generation as a controlled text generation problem using large datasets and conditioning on dialogue, cues, topics, and emotions.

Findings

Language models can generate plausible cues for play scripts.

Controlled generation improves cue relevance and attribute control.

The approach outperforms baseline methods in qualitative assessments.

Abstract

In this paper, we use a large-scale play scripts dataset to propose the novel task of theatrical cue generation from dialogues. Using over one million lines of dialogue and cues, we approach the problem of cue generation as a controlled text generation task, and show how cues can be used to enhance the impact of dialogue using a language model conditioned on a dialogue/cue discriminator. In addition, we explore the use of topic keywords and emotions for controlled text generation. Extensive quantitative and qualitative experiments show that language models can be successfully used to generate plausible and attribute-controlled texts in highly specialised domains such as play scripts. Supporting materials can be found at: https://catlab-team.github.io/cuegen.