DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

TL;DR

This paper introduces DLVGen, a novel dual latent variable model that generates personalized dialogue responses without requiring explicit persona data or dialogue examples, enhancing diversity and personalization.

Contribution

DLVGen is the first model to jointly model latent distributions over responses and personas, enabling personalized dialogue generation without explicit persona information or examples.

Findings

Generates diverse, persona-consistent responses

Operates without explicit persona data or dialogue examples

Outperforms baseline models in personalization and diversity

Abstract

The generation of personalized dialogue is vital to natural and human-like conversation. Typically, personalized dialogue generation models involve conditioning the generated response on the dialogue history and a representation of the persona/personality of the interlocutor. As it is impractical to obtain the persona/personality representations for every interlocutor, recent works have explored the possibility of generating personalized dialogue by finetuning the model with dialogue examples corresponding to a given persona instead. However, in real-world implementations, a sufficient number of corresponding dialogue examples are also rarely available. Hence, in this paper, we propose a Dual Latent Variable Generator (DLVGen) capable of generating personalized dialogue in the absence of any persona/personality information or any corresponding dialogue examples. Unlike prior work, DLVGen models the latent distribution over potential responses as well as the latent distribution over the agent's potential persona. During inference, latent variables are sampled from both distributions and fed into the decoder. Empirical results show that DLVGen is capable of generating diverse responses which accurately incorporate the agent's persona.