Knowledge transfer between speakers for personalised dialogue management

By Iñigo Casanueva, Thomas Hain, Heidi Christensen, Ricard Marxer, Phil D. Green. 2015

47 citations recorded by the source corpus.

Model-free reinforcement learning has been shown to be a promising data driven approach for automatic dialogue policy optimization, but a relatively large amount of dialogue interactions is needed before the system reaches reasonable performance. Recently, Gaussian process based reinforcement learning methods have been shown to reduce the number of dialogues needed to reach optimal performance, and pre-training the policy with data gathered from different dialogue systems has further reduced this amount. Following this idea, a dialogue system designed for a single speaker can be initialised with data from other speakers, but if the dynamics of the speakers are very different the model will have a poor performance. When data gathered from different speakers is available, selecting the data from the most similar ones might improve the performance. We propose a method which automatically selects the data to transfer by defining a similarity measure between speakers, and uses this measure to weight the influence of the data from each speaker in the policy model. The methods are tested by simulating users with different severities of dysarthria interacting with a voice enabled environmental control system.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Challenges in Building Intelligent Open-domain Dialog Systems (2019, methodology): “he chosen key-value pair forward and backward. This model can be trained on generic dialogue data without user identifier. XiaoIce also uses an explicit personalization model [132]. In the studies of [7, 54, 96, 120], personalized conversation generation is cast as domain adaptation or transfer lear”
Feudal Reinforcement Learning for Dialogue Management in Large Domains (2018, background): “Reinforcement Learning (RL) (Sutton and Barto, 1999) has been studied for several years as a promising approach to model dialogue management (Levin et al., 1998; Henderson et al., 2008; Pietquin et al., 2011; Young et al., 2013; Casanueva et al., 2015; Su et al., 2016).”
Transfer Learning for User Adaptation in Spoken Dialogue Systems (2016, background): “In [5], on a specific user adaptation problem, three different metrics are tested and yield heterogeneous results.”
Fine Grained Knowledge Transfer for Personalized Task-oriented Dialogue Systems (2017, background): “Learning based task-oriented dialogue systems (Casanueva et al. 2015; Genevay and Laroche 2016; Gaˇsic et al. 2013; Gasic et al. 2014; Williams and Zweig 2016; Bordes and Weston 2016) can select appropriate answers from a set of predeﬁned answers.”
On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems (2016, methodology): “In the context of spoken dialogue systems it has been successfully used for RL policy optimisation (Gašić and Young, 2014; Casanueva et al., 2015) and IRL reward function regression (Kim et al.”
Personalizing a Dialogue System With Transfer Reinforcement Learning (2016, methodology): “2015) and learning-based dialogue systems (Casanueva et al. 2015; Genevay and Laroche 2016).”
Neural personalized response generation as domain adaptation (2017, background): “[9] proposed an approach to automatically gathering dialogue data from similar speakers to improve the performance of personalized dialogue policy learning.”