Reconstructive Explanation: Explanation as Complex Problem Solving
Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Tools. Pages 135-139.
Abstract
Existing explanation facilities are typically far more appropriate for knowledge engineers engaged in system maintenance than for endusers of the system. This is because the explanation is little more than a trace of the detailed problem-solving steps. An alternative approach recognizes that an effective explanation often needs to substantially reorganize the line of reasoning and bring to bear additional information to support the result. Explanation itself becomes a complex problem-solving process that depends not only on the line of reasoning, but also on additional knowledge of the domain . We present a new computational model of explanation and argue that it results in significant improvements over traditional approaches.
@inproceedings{ijcai1989p22,
title = {Reconstructive Explanation: Explanation as Complex Problem Solving},
author = {Wick, Michael R. and Thompson, William B.},
booktitle = {Proceedings of the Eleventh International Joint Conference on
Artificial Intelligence, {IJCAI-89}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {N. S. Sridharan},
pages = {135--139},
year = {1989},
month = {8},
note = {Tools},
url = {https://ijcai.org/proceedings/1989/22},
}
TY - CPAPER TI - Reconstructive Explanation: Explanation as Complex Problem Solving AU - Wick, Michael R. AU - Thompson, William B. T2 - Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, IJCAI-89 PB - International Joint Conferences on Artificial Intelligence PY - 1989 SP - 135 EP - 139 UR - https://ijcai.org/proceedings/1989/22 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
