DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

Jing Yang Lee, Kong Aik Lee, Woon Seng Gan

2022

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.

Download


Paper Citation


in Harvard Style

Lee J., Lee K. and Gan W. (2022). DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 193-202. DOI: 10.5220/0010812500003116


in Bibtex Style

@conference{icaart22,
author={Jing Yang Lee and Kong Aik Lee and Woon Seng Gan},
title={DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={193-202},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010812500003116},
isbn={978-989-758-547-0},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation
SN - 978-989-758-547-0
AU - Lee J.
AU - Lee K.
AU - Gan W.
PY - 2022
SP - 193
EP - 202
DO - 10.5220/0010812500003116