Explanations in knowledge systems: design for explainable expert systems

By William R. Swartout, Cécile Paris, Johanna D. Moore. 1991

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, neutral): “…and Benbasat, 2003; Polson and Richardson, 1988; Psotka, Massey, and Mutter, 1988; Ritter and Feurzeig, 1988; Silverman, 1992; Sleeman and Brown, 1982; Southwick, 1991; Swartout, Paris, and Moore, 1991; Tanner and Keuneke, 1991; Tintarev, 2007; Woolf, 2007; Woolf, Beck, Eliot, and Stern, 2001)”
What do we need to build explainable AI systems for the medical domain? (2017, background): “There is some related work available on how to make such systems explainable (Shortliﬀe and Buchanan, 1975; Swartout et al., 1991; Johnson, 1994; Lacave and Diez, 2002).”
Causability and explainability of artificial intelligence in medicine (2019, methodology): “This was the basis for explanation, and there is some early related work available, for example, (Johnson, 1994; Lacave & Diez, 2002; Swartout, Paris, & Moore, 1991).”
Planning Text for Advisory Dialogues: Capturing Intentional and Rhetorical Information (1993, background): “Interested readers may find a thorough treatment of this topic in (Swartout 1983; Clancey 1983; Neches et al. 1985; Swartout et al. 1991; Moore and Paris 1991).”
Explanation and Argumentation Capabilities:Towards the Creation of More Persuasive Agents (2002, background): “The xplain system (Swartout 1983; Neches et al. 1985; Swartout et al. 1991) provides deep explanations by using the trace that an automatic programmer leaves behind and a high-level knowledge base representing domain facts and problem-solving plans.”
A Survey on the Explainability of Supervised Machine Learning (2020, background): “If the user fails to understand an explanation, the system should provide further knowledge in order to satisfy the user’s needs (Swartout et al., 1991).”
Introduction to the Special Issue on Explanation in Case-Based Reasoning (2005, background): “The importance of intelligent systems having the ability to explain their reasoning is well recognized (e.g., Buchanan and Shortliffe 1984; Southwick 1991; Swartout et al., 1991; Leake 1996; Herlocker et al., 2000; McSherry 2001).”
A New Approach To Expert System Explanations (1998, background): “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…”
Interpretable R-CNN (2017, background): “These early rule-based systems can generate theorem proving types of interpretable justifications [64, 68, 32, 41, 71], but were much less effective, too expensive to build and too brittle against the complexities of the real world.”
Designs for explaining intelligent agents (2009, background): “Examples of ontological explanations include the original Mycin explanation facility (Buchanan and Shortliffe, 1984), which provides access to its rule base via a simple stack trace mechanism, and the Explainable Expert System (EES) project (Swartout et al., 1991), which provides design rationale fo”
Explaining Recommendations: Satisfaction vs. Promotion (2005, background): “In the development of expert systems for medicine and other tasks, systems’ ability to explain their reasoning has been found to be critical to users’ acceptance of their decisions [14].”
Explanation and Justification in Machine Learning : A Survey Or (2017, background): “[ Swartout et al. , 1991 ] is a later example of such a framework.”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “It has evolved from being a niche research topic within the larger field of Artificial Intelligence (AI) [1–3] to becoming a highly active field of research, with a large number of theoretical contributions, empirical studies, and reviews being proposed every year [4,5].”
Stakeholders in Explainable AI (2018, background): “The latter problem led to approaches aimed at re-engineering knowledge bases to make the elements of the machine reasoning more recognisable, and to make the generated explanations more trustworthy (Swartout, Paris, and Moore 1991).”
Asking 'Why' in AI: Explainability of intelligent systems - perspectives and challenges (2018, background): “…Expert Systems (EES) project further developed the theme of using meta-knowledge for explanation generation, focusing on three key principles (Swartout, Paris, and Moore, 1991; Paris, 1993): (i) separation of terminological and declarative domain knowledge from procedural problem-solving…”