Log In Sign Up

Taming Continuous Posteriors for Latent Variational Dialogue Policies

by   Marin Vlastelica, et al.

Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optimizing dialogue success. Until now, categorical posteriors have been argued to be one of the main drivers of performance. In this work we revisit Gaussian variational posteriors for latent-action RL and show that they can yield even better performance than categoricals. We achieve this by simplifying the training procedure and propose ways to regularize the latent dialogue policy to retain good response coherence. Using continuous latent representations our model achieves state of the art dialogue success rate on the MultiWOZ benchmark, and also compares well to categorical latent methods in response coherence.


page 3

page 5

page 12


LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization

Reinforcement learning (RL) can enable task-oriented dialogue systems to...

DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context

Recently, reinforcement learning (RL) has been applied to task-oriented ...

Latent Intention Dialogue Models

Developing a dialogue agent that is capable of making autonomous decisio...

Hybrid Supervised Reinforced Model for Dialogue Systems

This paper presents a recurrent hybrid model and training procedure for ...

Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

A dialogue policy module is an essential part of task-completion dialogu...

Semi-Supervised Variational Reasoning for Medical Dialogue Generation

Medical dialogue generation aims to provide automatic and accurate respo...

MALA: Cross-Domain Dialogue Generation with Action Learning

Response generation for task-oriented dialogues involves two basic compo...