Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions

TL;DR

This paper enhances persona-grounded dialog models by expanding persona descriptions with commonsense knowledge and enabling discrete persona choices, leading to more natural, diverse, and consistent conversations.

Contribution

It introduces a novel method for expanding persona descriptions using commonsense knowledge and models discrete persona choices with variational learning.

Findings

Outperforms baselines in dialog quality and diversity

Achieves better persona consistency and controllability

Enables richer, more human-like conversations

Abstract

Existing persona-grounded dialog models often fail to capture simple implications of given persona descriptions, something which humans are able to do seamlessly. For example, state-of-the-art models cannot infer that interest in hiking might imply love for nature or longing for a break. In this paper, we propose to expand available persona sentences using existing commonsense knowledge bases and paraphrasing resources to imbue dialog models with access to an expanded and richer set of persona descriptions. Additionally, we introduce fine-grained grounding on personas by encouraging the model to make a discrete choice among persona sentences while synthesizing a dialog response. Since such a choice is not observed in the data, we model it using a discrete latent random variable and use variational learning to sample from hundreds of persona expansions. Our model outperforms competitive baselines on the PersonaChat dataset in terms of dialog quality and diversity while achieving persona-consistent and controllable dialog generation.