Evaluating the Markov assumption in Markov Decision Processes for spoken dialogue management
Guardado en:
| Publicado en: | Language Resources and Evaluation vol. 40, no. 1 (Feb 2006), p. 47-66 |
|---|---|
| Autor principal: | |
| Otros Autores: | |
| Publicado: |
Springer Nature B.V.
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 214793002 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1574-020X | ||
| 022 | |a 1574-0218 | ||
| 022 | |a 0010-4817 | ||
| 024 | 7 | |a 10.1007/s10579-006-9008-2 |2 doi | |
| 035 | |a 214793002 | ||
| 045 | 2 | |b d20060201 |b d20060228 | |
| 084 | |a 15327 |2 nlm | ||
| 100 | 1 | |a Paek, Tim | |
| 245 | 1 | |a Evaluating the Markov assumption in Markov Decision Processes for spoken dialogue management | |
| 260 | |b Springer Nature B.V. |c Feb 2006 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a The goal of dialogue management in a spoken dialogue system is to take actions based on observations and inferred beliefs. To ensure that the actions optimize the performance or robustness of the system, researchers have turned to reinforcement learning methods to learn policies for action selection. To derive an optimal policy from data, the dynamics of the system is often represented as a Markov Decision Process (MDP), which assumes that the state of the dialogue depends only on the previous state and action. In this article, we investigate whether constraining the state space by the Markov assumption, especially when the structure of the state space may be unknown, truly affords the highest reward. In simulation experiments conducted in the context of a dialogue system for interacting with a speech-enabled web browser, models under the Markov assumption did not perform as well as an alternative model which classifies the total reward with accumulating features. We discuss the implications of the study as well as its limitations. [PUBLICATION ABSTRACT] | |
| 653 | |a Markov analysis | ||
| 653 | |a Decision making models | ||
| 653 | |a Verbal communication | ||
| 653 | |a Voice communication | ||
| 653 | |a Speech | ||
| 653 | |a Reinforcement | ||
| 653 | |a Beliefs | ||
| 653 | |a Computer simulation | ||
| 653 | |a Optimization | ||
| 653 | |a Markov chains | ||
| 653 | |a Simulation | ||
| 653 | |a Experiments | ||
| 653 | |a Action | ||
| 653 | |a Assumptions | ||
| 653 | |a Models | ||
| 653 | |a Robustness | ||
| 653 | |a Alternative approaches | ||
| 700 | 1 | |a David Maxwell Chickering | |
| 773 | 0 | |t Language Resources and Evaluation |g vol. 40, no. 1 (Feb 2006), p. 47-66 | |
| 786 | 0 | |d ProQuest |t Arts & Humanities Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/214793002/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/214793002/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/214793002/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |