The Epistemology of a Rule-Based Expert System - A Framework for Explanation

By William J. Clancey. 1981

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Explainable Recommendation: A Survey and New Perspectives (2018, background): “For example, the work of Clancy showed that being able to explain predictions required far more knowledge than just making correct predictions (Clancey [1982]).”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “Early knowledge representation and reasoning systems typically aimed to meet this requirement by producing explanations for their outputs, for instance by presenting derivations from rules in rule-based architecture [69, 8], or graphical representations of nodes and edges in the case of Bayesian net”
Interacting meaningfully with machine learning systems: Three experiments (2009, background): “The bulk of the literature on explaining intelligent systems has focused on explaining expert systems based on deductive logic or rules (Swartout, 1983; Clancey, 1983; Wick and Thompson, 1992; Johnson, 1994).”
Explanation in Case-Based Reasoning–Perspectives and Goals (2005, background): “Examples are MYCIN’s how and why explanations (Clancey, 1983).”
Beyond the Repertory Grid: New Approaches to Constructivist Knowledge Acquisition Tool Development (1993, unknown): “However , Clancey 81 has eloquently argued for the necessity and irreducibility of classification models , and researchers such as Gaines 36 have demonstrated elegant approaches to resource allocation problems based entirely on classification .”
Explanation and Argumentation Capabilities:Towards the Creation of More Persuasive Agents (2002, background): “In neomycin (Clancey 1983b, Hasling et al. 1984), control between the different processing stages is represented by meta-rules.”
From Guidon to Neomycin and Heracles in twenty short lessons (1986, methodology): “However, TEIRESIAS’s metarules compose domain facts with procedure, just like MYCIN’s rules (Clancey 1983a).”
Designs for explaining intelligent agents (2009, background): “…assist with physician training, they realized that explanation facilities were central to exposing the system’s reasoning steps, how a request for information translated into a system process, and the relationship between system goals and how these goals or outcomes were achieved (Clancey, 1983).”