Explanation: the role of control strategies and deep models
Expert systems: the user interface
Cognitive impacts of the user interface
Expert systems: the user interface
Providing responses specific to a user's goals and background
International Journal of Expert Systems
A philosophical basis for knowledge acquisition
Knowledge Acquisition
Reconstructive expert system explanation
Artificial Intelligence
Knowledge Acquisition - Special issue on knowledge acquisition for therapy-planning tasks
Explanation in second generation expert systems
Second generation expert systems
Case-based reasoning
Advances in knowledge discovery and data mining
An integrated environment for knowledge acquisition
Proceedings of the 6th international conference on Intelligent user interfaces
Computer science as empirical inquiry: symbols and search
Communications of the ACM
Knowledge Acquisition without Analysis
Proceedings of the 7th European Workshop on Knowledge Acquisition for Knowledge-Based Systems
Presenting Significant Information in Expert System Explanation
EPIA '95 Proceedings of the 7th Portuguese Conference on Artificial Intelligence: Progress in Artificial Intelligence
Model-Based Visualization of Temporal Abstractions
TIME '98 Proceedings of the Fifth International Workshop on Temporal Representation and Reasoning
Validating knowledge acquisition: multiple classification ripple-down rules
Validating knowledge acquisition: multiple classification ripple-down rules
Software psychology: Human factors in computer and information systems (Winthrop computer systems series)
A brief historical review of explanation in expert system applications
AIAP'07 Proceedings of the 25th conference on Proceedings of the 25th IASTED International Multi-Conference: artificial intelligence and applications
Epistemological Approach to the Process of Practice
Minds and Machines
Improving understandability of semantic search explanations
International Journal of Knowledge Engineering and Data Mining
Constructing understandable explanations for semantic search results
EKAW'10 Proceedings of the 17th international conference on Knowledge engineering and management by the masses
| Hi-index | 0.01 |
The ability to provide explanations has been seen as a key feature of expert systems (ES) typically not offered by other types of computer systems. ES need to offer explanations because of imprecise domains and the use of heuristics. Verification is not enough. ES need to justify and be accountable. Explanation is seen as an important activity for knowledge-based systems as it satisfies the user's need to decide whether to accept or reject a recommendation. In this paper we review explanation in first-generation and second-generation ES. An alternative is offered to the main approaches which uses multiple classification ripple-down rules and challenges even the goals of explanation. Instead of trying to give explanations which provide a meaningful line of reasoning and which are tailored to suit the individual it may be just as useful to provide the user with sufficient information and browsing tools to develop their own line of reasoning. The type of information that can assist understanding is the context in which the recommendation applies (which is provided through the display of relevant cases and exception rule history) and the ability to explore an abstraction hierarchy of the rules using formal concept analysis. An explanation toolkit aimed at putting the user in control is described and evaluated in this paper.