Reconstructive Expert System Explanation

By Michael R. Wick, W. B. Thompson. 1992

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

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “engineers transparency during development of the system (Wallis and Shortliffe, 1981), and verification, duplication, and ratification (Wick and Thompson, 1992) explaining how a system reached an answer, justifying why an answer is good clarifying concepts, and teaching a user about the domain…”
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (2016, background): “Humans are surprisingly good at explaining their decisions, even though their explanations do not necessarily align with their initial reasoning [36].”
The FacT: Taming Latent Factor Models for Explainability with Factorization Trees (2019, background): “sk of recommendation learning, there is still no guarantee on the fidelity of provided explanations. The idea of providing rule-based explanations was popularized in the development of expert systems [15, 36]. For example, MYCIN [31], a rule-based reasoning system, provides explanations by translati”
Explanation in Probabilistic Systems: Is It Feasible? Will It Work? (2001, background): “Explanation has been postulated to be a complex problem solving process depending not only on the actual line of reasoning, but also on additional knowledge of the domain [31].”
A historical perspective of explainable Artificial Intelligence (2020, methodology): “Explanations in these systems consist of either descriptions coupled to the reasoning trace of the system, or descriptions more coupled to the story behind the decision-making process of the system (Buchanan & Shortliffe, 1984; Wick & Thompson, 1992).”
Designing and Evaluating Explanations for Recommender Systems (2011, background): “This research has largely been focused on what kind of explanations can be generated and how these have been implemented in real world systems [8, 32, 38, 66].”
Explaining Recommendations: Design and Evaluation (2015, background): “Explanations in advisory systems are not a new idea: explanations have often been considered as part of the research in the area of advisory expert systems [6, 33, 38, 44, 86].”
Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making (2018, background): “d statistically assess it, assure it, or get closer to it [64, 32,23]. Research stemming from the early days of machine learning in expert systems attempts to make algorithmic logics more transparent [75,81,54,66], or to better understand how users work with inductive systems and build mental models”
A review of explanation methods for Bayesian networks (2002, background): “Other systems try to offer a simple but comprehensible report about the domain and the reasoning (Carolis et al., 1996; Chandrasekaran et al., 1989; Horvitz et al., 1986; Langlotz et al., 1988; Reggia & Perricone, 1985; Strat, 1987; Swartout, 1983; Wick & Slagle, 1989, Wick & Thompson, 1992).”
Explaining models: an empirical study of how explanations impact fairness judgment (2019, background): “Accordingly, Wick and Thompson discussed the taxonomy of global-local explanations [37].”
A generalized taxonomy of explanations styles for traditional and social recommender systems (2012, background): “Explanation in intelligent systems has its origins in the area of Expert Systems (Andersen et al. 1989; Buchanan and Shortliffe 1984; Hunt and Price 1988; LopezSuarez and Kamel 1994; Wick and Thompson 1992; Lacave and Diez 2004).”
Explanation in Case-Based Reasoning–Perspectives and Goals (2005, methodology): “Wick and Thompson (1992) argue that explanation should be viewed as a problem-solving process separate from the process used to determine the conclusion in the first place.”