论文信息 - Context-Aware Conversational Agents Using POMDPs and Agenda-Based Simulation

Context-Aware Conversational Agents Using POMDPs and Agenda-Based Simulation

Context-aware systems in combination with mobile devices offer new opportunities in the areas of knowledge representation, natural language processing and intelligent information retrieval. Our vision is that natural spoken conversation with these devices can eventually become the preferred mode for managing their services by means of conversational agents. In this paper, we describe the application of POMDPs and agenda-based user simulation to learn optimal dialog policies for the dialog manager in a conversational agent. We have applied this approach to develop a statistical dialog manager for a conversational agent which acts as a voice logbook to collect home monitored data from patients suffering from diabetes.

David Griol | José M. Molina | D. Griol | J. M. Molina

[1] Leslie Pack Kaelbling,et al. Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[2] David Griol,et al. A statistical approach to spoken dialog systems design and evaluation , 2008, Speech Commun..

[3] Hui Ye,et al. Training a real-world POMDP-based Dialog System , 2007, HLT-NAACL 2007.

[4] Steve Young,et al. The statistical approach to the design of spoken dialogue systems , 2003 .

[5] Michael F. McTear,et al. Appraisal of a conversational artefact and its utility in remote patient monitoring , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[6] David Griol,et al. An Architecture to Provide Context-Aware Services by Means of Conversational Agents , 2010, DCAI.

[7] Roberto Pieraccini,et al. A stochastic model of human-machine interaction for learning dialog strategies , 2000, IEEE Trans. Speech Audio Process..