Tailoring Explanations for the User
Abstract
In order for an expert system to provide the most effective explanations, it should be able to tailor its responses to the concerns of the user. One way in which explanations may be tailored is by point of view A method is presented for representing the knowledge to support different points of view in the current domain. In addition, we present a method for determining the point of view to take by inferring the user's goal within a brief discourse segment. The advising system's response to the derived goal depends on the strength of its belief in the inference for which a method of determination is also provided. This information enables the system to decide what answer to give to a question, which kind of justification is relevant, and when to provide it. Some details of the current implementation are included.
Cite
Text
McKeown et al. "Tailoring Explanations for the User." International Joint Conference on Artificial Intelligence, 1985. doi:10.7916/D8SB4DRZMarkdown
[McKeown et al. "Tailoring Explanations for the User." International Joint Conference on Artificial Intelligence, 1985.](https://mlanthology.org/ijcai/1985/mckeown1985ijcai-tailoring/) doi:10.7916/D8SB4DRZBibTeX
@inproceedings{mckeown1985ijcai-tailoring,
title = {{Tailoring Explanations for the User}},
author = {McKeown, Kathleen R. and Wish, Myron and Matthews, Kevin},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1985},
pages = {794-798},
doi = {10.7916/D8SB4DRZ},
url = {https://mlanthology.org/ijcai/1985/mckeown1985ijcai-tailoring/}
}