Dialogue manager domain adaptation using Gaussian process reinforcement learning

Change log
Gašić, M 
Mrkšić, N 
Rojas-Barahona, LM 
Su, PH 

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.

Dialogue systems, Reinforcement learning, Gaussian process
Journal Title
Computer Speech and Language
Conference Name
Journal ISSN
Volume Title
Elsevier BV
Engineering and Physical Sciences Research Council (EP/M018946/1)
Engineering and Physical Sciences Research Council (Grant ID: EP/M018946/1 ”Open Domain Statistical Spoken Dialogue Systems”)
Is supplemented by: