PARADISE: A Framework for Evaluating Spoken Dialogue Agents

13 years 5 months ago

Download www.media.mit.edu

This paper presents PARADISE (PARAdigm for DIalogue System Evaluation), a general framework for evaluating spoken dialogue agents. The framework decouples task requirements from an agent’s dialogue behaviors, supports comparisons among dialogue strategies, enables the calculation of performance over subdialogues and whole dialogues, speciﬁes the relative contribution of various factors to performance, and makes it possible to compare agents performing different tasks by normalizing for task complexity.

Marilyn A. Walker, Diane J. Litman, Candace A. Kam

Real-time Traffic

ACL 1997 | ACL 2007 | Dialogue | DIalogue System Evaluation | Spoken Dialogue Agents |

claim paper

» Learning Optimal Dialogue Strategies A Case Study of a Spoken Dialogue Agent for Email

» An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialog...

» Evaluating Response Strategies in a WebBased Spoken Dialogue Agent

» Quantitative and Qualitative Evaluation of Darpa Communicator Spoken Dialogue Systems

» Predicting and Adapting to Poor Speech Recognition in a Spoken Dialogue System

» Evaluation of a hierarchical reinforcement learning spoken dialogue system

» Comparing Objective and Subjective Measures of Usability in a HumanRobot Dialogue System

» AgentBased Adaptive Interaction and Dialogue Management Architecture for Speech Applicatio...

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	1997
Where	ACL
Authors	Marilyn A. Walker, Diane J. Litman, Candace A. Kamm, Alicia Abella

Comments (0)

Sciweavers

PARADISE: A Framework for Evaluating Spoken Dialogue Agents

ACL 1997 | ACL 2007 | Dialogue | DIalogue System Evaluation | Spoken Dialogue Agents |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers