Abstract
This paper describes a framework to construct interface agents with example dialogs based on the tasks by the machine learning technology. The Wizard of Oz method is used to collect example dialogs, and a finite state machine-based model is used for the dialog model. We implemented a Web-based system which includes these functions, and empirically examined the system which treats with a guide task in Kyoto through the experimental use.
| Original language | English |
|---|---|
| Title of host publication | Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings |
| Editors | Franco Zambonelli, Matthias Klusch |
| Publisher | Springer Verlag |
| Pages | 20-25 |
| Number of pages | 6 |
| ISBN (Electronic) | 3540425454, 9783540425458 |
| Publication status | Published - 2001 Jan 1 |
| Event | 5th International Workshop on Cooperative Information Agents, CIA 2001 - Modena, Italy Duration: 2001 Sep 6 → 2001 Sep 8 |
Publication series
| Name | Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) |
|---|---|
| Volume | 2182 |
| ISSN (Print) | 0302-9743 |
Conference
| Conference | 5th International Workshop on Cooperative Information Agents, CIA 2001 |
|---|---|
| Country | Italy |
| City | Modena |
| Period | 01/9/6 → 01/9/8 |
ASJC Scopus subject areas
- Theoretical Computer Science
- Computer Science(all)
Fingerprint Dive into the research topics of 'Wizard of Oz method for learning dialog agents'. Together they form a unique fingerprint.
Cite this
Okamoto, M., Yang, Y., & Ishida, T. (2001). Wizard of Oz method for learning dialog agents. In F. Zambonelli, & M. Klusch (Eds.), Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings (pp. 20-25). (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2182). Springer Verlag.