Explanation and interaction: the computer generation of explanatory dialogues
Explanation and interaction: the computer generation of explanatory dialogues
Automatic Program DeBugging for Intelligent Tutoring Systems
Automatic Program DeBugging for Intelligent Tutoring Systems
Rule Based Expert Systems: The Mycin Experiments of the Stanford Heuristic Programming Project (The Addison-Wesley series in artificial intelligence)
A review of explanation methods for heuristic expert systems
The Knowledge Engineering Review
Proceedings of the 3rd international conference on Knowledge capture
Learning and joint deliberation through argumentation in multiagent systems
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
An argumentation-based framework for deliberation in multi-agent systems
ArgMAS'07 Proceedings of the 4th international conference on Argumentation in multi-agent systems
Visualizing Semantic Web proofs of defeasible logic in the DR-DEVICE system
Knowledge-Based Systems
Automated interpretation of key performance indicator values and its application in education
Knowledge-Based Systems
| Hi-index | 0.00 |
Explanation is an important feature that needs to be integrated into software products. Early software that filled the horizontal software market (such as word processors) contained help systems. More specialized systems, known as expert systems, were developed to produce solutions that required specific domain knowledge of the problem being solved. The expert systems initially produced results that were consistent with the results produced by experts, but the expert systems only mimicked the rules the experts outlined. The decisions provided by expert systems include no justification, thus causing users to doubt the results reported by the system. If the user was dealing with a human expert, he could ask for a line of reasoning used to draw the conclusion. The line of reasoning provided by the human expert could then be inspected for discrepancies by another expert or verified in some other manner. Software systems need better explanations of how to use them and how they produce results. This will allow the users to take advantage of the numerous features being provided and increase their trust in the software product.