Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

NAACL
2007

favoriteEmaildiscussreport

125views Computational Linguistics» more NAACL 2007»

Comparing User Simulation Models For Dialog Strategy Learning

13 years 6 months ago

Comparing User Simulation Models For Dialog Strategy Learning

Download www.cs.pitt.edu

This paper explores what kind of user simulation model is suitable for developing a training corpus for using Markov Decision Processes (MDPs) to automatically learn dialog strategies. Our results suggest that with sparse training data, a model that aims to randomly explore more dialog state spaces with certain constraints actually performs at the same or better than a more complex model that simulates realistic user behaviors in a statistical way.

Hua Ai, Joel R. Tetreault, Diane J. Litman

Real-time Traffic

Computational Linguistics | Dialog Strategies | NAACL 2007 | Realistic User Behaviors | User Simulation Model |

claim paper

Related Content

» User simulation in a stochastic dialog system

» A Statistical User Simulation Technique for the Improvement of a Spoken Dialog System

» Combining user intention and error modeling for statistical dialog simulators

» Setting Up User Action Probabilities in User Simulations for Dialog System Development

» Semiautomatic Creation of Resources for Spoken Dialog Systems

» Efficient model learning for dialog management

» Learning Dialogue Strategies from Older and Younger Simulated Users

» Experience sampling for building predictive user models a comparative study

» Consistent GoalDirected User Model for Realisitc ManMachine TaskOriented Spoken Dialogue S...

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2007
Where	NAACL
Authors	Hua Ai, Joel R. Tetreault, Diane J. Litman

Comments (0)