Dialogue manager domain adaptation using Gaussian process reinforcement learning

TL;DR

This paper presents a Gaussian process reinforcement learning framework for domain adaptation in dialogue managers, enabling more flexible, data-efficient, and uncertainty-aware dialogue systems across multiple domains.

Contribution

It extends Gaussian process reinforcement learning to handle multiple dialogue domains, incorporating prior knowledge and multi-agent learning for adaptable dialogue management.

Findings

Supports multi-domain dialogue modeling

Incorporates prior knowledge and Bayesian methods

Enhances adaptability and data efficiency

Abstract

Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a computer interface can facilitate swift, human-like acquisition of information. In recent years, speech interfaces have become ever more popular, as is evident from the rise of personal assistants such as Siri, Google Now, Cortana and Amazon Alexa. Recently, data-driven machine learning methods have been applied to dialogue modelling and the results achieved for limited-domain applications are comparable to or outperform traditional approaches. Methods based on Gaussian processes are particularly effective as they enable good models to be estimated from limited training data. Furthermore, they provide an explicit estimate of the uncertainty which is particularly useful for reinforcement learning. This article explores the additional steps that are necessary to extend these methods to model multiple dialogue domains. We show that Gaussian process reinforcement learning is an elegant framework that naturally supports a range of methods, including prior knowledge, Bayesian committee machines and multi-agent learning, for facilitating extensible and adaptable dialogue systems.