Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
This addresses the challenge of enhancing human-AI collaboration in creative storytelling, though it is incremental as it builds on existing conversational agents.
The paper tackles the problem of designing an AI agent for collaborative dialogue to create engaging narratives by controlling information revelation, resulting in improved accuracy in predicting next dialogue lines and preference from professional performers.
We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the goal is to establish universe details, and to collaborate on an interesting story in that universe, through a series of natural dialogue exchanges. Our model can augment any probabilistic conversational agent by allowing it to reason about universe information established and what potential next utterances might reveal. Ideally, with each utterance, agents would reveal just enough information to add specificity and reduce ambiguity without limiting the conversation. We empirically show that our model allows control over the rate at which the agent reveals information and that doing so significantly improves accuracy in predicting the next line of dialogues from movies. We close with a case-study with four professional theatre performers, who preferred interactions with our model-augmented agent over an unaugmented agent.