Abstract
For robust spoken dialog management, various dialog state tracking methods have been proposed. Although discriminative models are gaining popularity due to their superior performance, generative models based on the Partially Observable Markov Decision Process model still remain attractive since they provide an integrated framework for dialog state tracking and dialog policy optimization. Although a straightforward way to fit a generative model is to independently train the component probability models, we present a gradient descent algorithm that simultaneously train all the component models. We show that the resulting tracker performs competitively with other top-performing trackers that participated in DSTC2.
| Original language | English |
|---|---|
| Title of host publication | SIGDIAL 2014 - 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 273-281 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781941643211 |
| DOIs | |
| Publication status | Published - 2014 |
| Externally published | Yes |
| Event | 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2014 - Philadelphia, United States Duration: 2014 Jun 18 → 2014 Jun 20 |
Publication series
| Name | SIGDIAL 2014 - 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference |
|---|
Conference
| Conference | 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2014 |
|---|---|
| Country/Territory | United States |
| City | Philadelphia |
| Period | 14/6/18 → 14/6/20 |
Bibliographical note
Publisher Copyright:© 2014 Association for Computational Linguistics.
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Modelling and Simulation
- Human-Computer Interaction