Abstract
One of the main problems with partially observable Markov decision process (POMDP) in development of spoken dialog system (SDS) is lack of scalability. In development of an SDS with electronic program guide (EPG) domain, we devised a POMDP approach which is operated with summary spaces to respond accurately to multiple drifting goals and massive numbers of slot entities. The main point of the proposed approach is to introduce a hybrid architecture that is implemented by a meta-action selector and a service provider. A trained POMDP policy was used to select meta-actions. The selected meta-actions were transformed to the system action in the service provider, which is implemented with the given system action model. By using this architecture, various system actions could be elicited with reduced complexity in the dialog process. We trained the system with the specified simulator and observed its behavior with learning curves in the Korean EPG domain. The convergence of learning curve implies the feasibility of our approach in commercial EPG domain SDS.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
