Unsupervised Enrichment of Persona-grounded Dialog with Background Stories

TL;DR

This paper introduces an unsupervised method to enrich persona-grounded dialogue with background stories from fictional narratives, resulting in more diverse, engaging, and human-like responses.

Contribution

It proposes a novel unsupervised approach to incorporate background stories into dialog models using gradient-based rewriting, enhancing response diversity and engagement.

Findings

Responses are more diverse and engaging.

Generated responses are rated more human-like.

Method outperforms existing dialog models.

Abstract

Humans often refer to personal narratives, life experiences, and events to make a conversation more engaging and rich. While persona-grounded dialog models are able to generate responses that follow a given persona, they often miss out on stating detailed experiences or events related to a persona, often leaving conversations shallow and dull. In this work, we equip dialog models with 'background stories' related to a persona by leveraging fictional narratives from existing story datasets (e.g. ROCStories). Since current dialog datasets do not contain such narratives as responses, we perform an unsupervised adaptation of a retrieved story for generating a dialog response using a gradient-based rewriting technique. Our proposed method encourages the generated response to be fluent (i.e., highly likely) with the dialog history, minimally different from the retrieved story to preserve event ordering and consistent with the original persona. We demonstrate that our method can generate responses that are more diverse, and are rated more engaging and human-like by human evaluators, compared to outputs from existing dialog models.