Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description

TL;DR

This paper introduces a novel method for dialogue personalization that predicts persona information from dialogue history, enabling more consistent and engaging responses without needing explicit persona descriptions during inference.

Contribution

It presents a new approach to dialogue personalization that predicts persona information from dialogue history, removing reliance on explicit persona descriptions at inference time.

Findings

Improves response consistency by conditioning on self persona.

Enhances engagingness by conditioning on partner persona.

Model transferability to other datasets improves relevance.

Abstract

Personalizing dialogue agents is important for dialogue systems to generate more specific, consistent, and engaging responses. However, most current dialogue personalization approaches rely on explicit persona descriptions during inference, which severely restricts its application. In this paper, we propose a novel approach that learns to predict persona information based on the dialogue history to personalize the dialogue agent without relying on any explicit persona descriptions during inference. Experimental results on the PersonaChat dataset show that the proposed method can improve the consistency of generated responses when conditioning on the predicted profile of the dialogue agent (i.e. "self persona"), and improve the engagingness of the generated responses when conditioning on the predicted persona of the dialogue partner (i.e. "their persona"). We also find that a trained persona prediction model can be successfully transferred to other datasets and help generate more relevant responses.