Spoken natural language dialog systems: a practical approach
Spoken natural language dialog systems: a practical approach
An architecture for voice dialog systems based on prolog-style theorem proving
Computational Linguistics
Collaborative plans for complex group action
Artificial Intelligence
Using Bayesian Networks to Manage Uncertainty in Student Modeling
User Modeling and User-Adapted Interaction
An Analysis of Initiative Selection in CollaborativeTask-Oriented Discourse
User Modeling and User-Adapted Interaction
User Modeling and User-Adapted Interaction
Predictive Statistical Models for User Modeling
User Modeling and User-Adapted Interaction
A plan-based analysis of indirect speech acts
Computational Linguistics
A collaborative planning model of intentional structure
Computational Linguistics
Methodologies for automated telephone answering
ISMIS'05 Proceedings of the 15th international conference on Foundations of Intelligent Systems
| Hi-index | 0.00 |
Dialog participants in a non-mixed initiative dialogs, in which one participant asks questions exclusively and the other participant responds to those questions exclusively, can select actions that minimize the expected length of the dialog. The choice of question that minimizes the expected number of questions to be asked can be computed in polynomial time in some cases.The polynomial-time solutions to special cases of the problem suggest a number of strategies for selecting dialog actions in the intractable general case. In a simulation involving 1000 dialog scenarios, an approximate solution using the most probable rule set/least probable question resulted in expected dialog length of 3.60 questions per dialog, as compared to 2.80 for the optimal case, and 5.05 for a randomly chosen strategy.