Dialogue manager domain adaptation using Gaussian process reinforcement learning. (September 2017)

• Record Type: Journal Article
• Authors: Gašić, Milica; Mrkšić, Nikola; Rojas-Barahona, Lina M.; Su, Pei-Hao; Ultes, Stefan; Vandyke, David; Wen, Tsung-Hsien; Young, Steve
• Is Part Of: Computer speech & language. Volume 45(2017)
• Page Start: 552
• Page End: 569
• Publication Date: 2017-09
• Subjects: Dialogue systems -- Reinforcement learning -- Gaussian process; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2016.09.003
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Generic-specific policy model. Policy committee model. Multi-agent policy model. Human user evaluation. 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 out-perform 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.