Explanation in second generation expert systems

By William R. Swartout, Johanna D. Moore. 1993

Subfields: Knowledge Graphs & Representation

How researchers see this paper

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

In Knowledge Graphs & Representation

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): “…and Díez, 2002; Miller, 2017; Miller, Howe, and Sonenberg, 2017; Miller et al., 2017; Moore and Swartout, 1988; Moulin, Irandoust, Bélanger, and Desbordes, 2002; Mueller and Klein, 2011; Sørmo, Cassens, and Aamodt, 2005; Swartout and Moore, 1993; Weston et al., 2015; Wick and Thompson, 1992).”
Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences (2017, background): “The term “explainable AI” has regained traction again recently, after being considered important in the 80s and 90s in expert systems particularly; see [Chandrasekaran et al. , 1989], [Swartout and Moore, 1993], and [Buchanan and Shortliﬀe, 1984].”
Improving Robot Controller Transparency Through Autonomous Policy Explanation (2017, background): “Complementing human-robot interaction literature focused on generating content and determining the relevance of information to communicate, prior work in the expert systems community has investigated and characterized the principal components of effective explanations [41]: constructing an expositor”
Infusing domain knowledge in AI-based "black box" models for better explainability with application in bankruptcy prediction (2019, background): “Research in Explainable Artificial Intelligence is an emerging field, seeing a resurgence after three decades of slowed progress since the work of Chandrasekaran et al. [29], Swartout et al. [70], and Buchanan et al. [69].”
A New Approach To Expert System Explanations (1998, unknown): “Two separate approaches have been proposed to address this problem: In the Explainable Expert System (EES) approach (Swartout et al., 1991; Swartout and Moore, 1993), the knowledge representation used by the expert system is enriched to include explicit \strategic" knowledge, i.e., knowledge about…”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Methods generating textual explanations are surveyed in [32] and compared according to some requirements about the structure and content of the explanations to adapt them to the users’ needs and knowledge.”
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (2019, methodology): “A segmentation network from [52] is capable of producing a semantic seg-”
Explanation and Argumentation Capabilities:Towards the Creation of More Persuasive Agents (2002, methodology): “To handle feedback, the system must (Swartout and Moore 1993): 1) interpret the follow-up questions in the context of the ongoing interaction, which includes the previous”
Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence (2021, background): “The problem of opacity can also arise for other AI paradigms (see, for example, [9]).”
Agents that Learn to Explain Themselves (1994, background): “Explanations based on traces of rule firings or paraphrases of rules tend not to be successful (Davis 1976; Swartout & Moore 1993; Clancey 198313).”
Design and Evaluation of Explainable BDI Agents (2010, background): “A lot of research on explanation has been done in the field of expert systems (e.g. [20]).”
Building Explainable Artificial Intelligence Systems (2006, background): “While novel, this research did not address how lessons learned from explaining expert system decisions ( Swartout & Moore 1993 ) applied to explaining the behavior of simulated entities.”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, background): “2 There is a large amount of surveys that provide an overview of explanations published elsewhere [223,222,214,42,57,79,156,126,127,209,160,178,200].”
Explainable Agency for Intelligent Autonomous Systems (2017, background): “Some early expert systems simply replayed their reasoning chains, which led Swartout and Moore (1993) to call for more sophisticated explanation facilities.”
Explanation in Case-Based Reasoning–Perspectives and Goals (2005, background): “In (Swartout and Moore, 1993), five requirements for the explanation capability of expert systems were put forth.”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, background): “general assessment of the overall practical value of an explanation, which further includes human factors, such as understandability, manageability, and overall utility of the XAI system [133], [147], [184].”