Mixed-Initiative Relaxation of Constraints in Critiquing Dialogues

Authors:
David Mcsherry;David W. Aha
Affiliations:
School of Computing and Information Engineering, University of Ulster, Coleraine BT52 1SA, Northern Ireland;Navy Center for Applied Research in Artificial Intelligence, Naval Research Laboratory, Code 5514, Washington DC 20375, USA
Venue:
ICCBR '07 Proceedings of the 7th international conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
Year:
2007

Citing 10
Cited 1

Conversational Case-Based Reasoning

Applied Intelligence
The FindMe Approach to Assisted Browsing

IEEE Expert: Intelligent Systems and Their Applications
Comparison-Based Recommendation

ECCBR '02 Proceedings of the 6th European Conference on Advances in Case-Based Reasoning
ITR: A Case-Based Travel Advisory System

ECCBR '02 Proceedings of the 6th European Conference on Advances in Case-Based Reasoning
Experiments in dynamic critiquing

Proceedings of the 10th international conference on Intelligent user interfaces
Advances in conversational case-based reasoning

The Knowledge Engineering Review
A personalized system for conversational recommendations

Journal of Artificial Intelligence Research
The ins and outs of critiquing

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Incremental critiquing

Knowledge-Based Systems
Similarity and compromise

ICCBR'03 Proceedings of the 5th international conference on Case-based reasoning: Research and Development

Conversational Case-Based Recommendations Exploiting a Structured Case Model

ECCBR '08 Proceedings of the 9th European conference on Advances in Case-Based Reasoning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Eliminating previously recommended items in a critiquing dialogue prevents the user from navigating back to acceptable items she critiqued earlier in the dialogue. An equally serious problem if previous recommendations are not eliminated is that acceptable items may be unreachable by any sequence of critiques. Progressive critiquing solves this dilemma while also making it easier for users to recognize when none of the available items are acceptable. In this paper, we present theoretical and empirical results that demonstrate the benefits of a critiquing strategy in which the user gives priority to constraints that must be satisfied in a progressive critiquing dialogue. We also present a new version of progressive critiquing in which mixed-initiative relaxation of constraints introduced by user critiquing choices that depart from this strategy greatly reduces their impact on dialogue outcomes.