Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues

by   Thibault Cordier, et al.
Université d'Avignon et des Pays de Vaucluse

Reinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues. However, the user simulator provided by state-of-the-art dialogue frameworks are only rough approximations of human behaviour. The ability to learn from a small number of human interactions is hence crucial, especially on multi-domain and multi-task environments where the action space is large. We therefore propose to use structured policies to improve sample efficiency when learning on these kinds of environments. We also evaluate the impact of learning from human vs simulated experts. Among the different levels of structure that we tested, the graph neural networks (GNNs) show a remarkable superiority by reaching a success rate above 80 dialogues, when learning from simulated experts. They also show superiority when learning from human experts, although a performance drop was observed, indicating a possible difficulty in capturing the variability of human strategies. We therefore suggest to concentrate future research efforts on bridging the gap between human data, simulators and automatic evaluators in dialogue frameworks.


page 1

page 2

page 3

page 4


Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues

Task-oriented dialogue systems are designed to achieve specific goals wh...

Task-oriented Dialogue Systems: performance vs. quality-optima, a review

Task-oriented dialogue systems (TODS) are continuing to rise in populari...

On the Evaluation of Dialogue Systems with Next Utterance Classification

An open challenge in constructing dialogue systems is developing methods...

Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems

Dialogue policy optimisation via reinforcement learning requires a large...

Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation

Human evaluation has been widely accepted as the standard for evaluating...

Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems

Task-oriented dialogue systems (TDSs) are assessed mainly in an offline ...

Structured Hierarchical Dialogue Policy with Graph Neural Networks

Dialogue policy training for composite tasks, such as restaurant reserva...

Please sign up or login with your details

Forgot password? Click here to reset