论文信息 - A Methodology for Learning Optimal Dialog Strategies

A Methodology for Learning Optimal Dialog Strategies

In this paper, we present a technique for learning new dialog strategies by using a statistical dialog manager that is trained from a dialog corpus. A dialog simulation technique has been developed to acquire data required to train the dialog model and then explore new dialog strategies. A set of measures has also been defined to evaluate the dialog strategy that is automatically learned. We have applied this technique to explore the space of possible dialog strategies for a dialog system that collects monitored data from patients suffering from diabetes.

[1] Steve J. Young,et al. A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies , 2006, The Knowledge Engineering Review.

[2] Kallirroi Georgila,et al. User simulation for spoken dialogue systems: learning and evaluation , 2006, INTERSPEECH.

[3] Steve J. Young,et al. Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[4] David Griol,et al. Acquiring and Evaluating a Dialog Corpus through a Dialog Simulation Technique , 2007, SIGdial.

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

[6] 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).

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