ABSTRACT. In the design of spoken dialogue systems that are robust to speech recognition and interpretation errors, modelling un- certainty is crucial.
Modelling user behaviour in the HIS-POMDP dialogue manager
www.researchgate.net › publication › 22...
This paper reports on the design and evaluation of the user act model (UAM) as part of the Hidden Information State (HIS) POMDP dialogue manager. Within this ...
By modelling dialogue as a POMDP (Partially Observable Markov Decision Process), a framework is provided that enables these uncertainties to be modelled in a ...
Readers on ; MODELLING USER BEHAVIOUR IN THE HIS-POMDP DIALOGUE MANAGER · Institute of Electrical and Electronics Engineers (IEEE), December 2008 · 10.1109/slt.
In this paper, we present a new reinforcement learning algorithm for user behavior modeling, which is based on POMDP (Partially Observable Markov Decision ...
Missing: HIS- | Show results with:HIS-
Abstract. We propose a novel approach to developing a dialogue model that is able to take into account some aspects of the user's affective state and to act.
Missing: behaviour | Show results with:behaviour
Modelling user behaviour in the HIS-POMDP dialogue manager ...
colab.ws › articles › SLT.2008.4777855
Modelling user behaviour in the HIS-POMDP dialogue manager. Keizer S., Gasic M., Mairesse F., Thomson B., Yu K., Young S. Expand. Publication type ...
Over several years, we have developed an approach to spoken dialogue systems that includes rule-based and trainable dialogue managers, spoken language ...
ABSTRACT. This paper explains how partially observable Markov decision pro- cesses (POMDPs) can provide a principled mathematical framework for modelling ...
Abstract. Intelligent planning algorithms such as the Partially Observ- able Markov Decision Process (POMDP) have succeeded in dialog management ...