Explanations in knowledge systems: Design for Explainable Expert Systems

William Swartout; Cécile Paris; Johanna Moore

doi:10.1109/64.87686

Explanations in knowledge systems: Design for Explainable Expert Systems

William Swartout, Cécile Paris, Johanna Moore

School of Computing

Research output: Contribution to journal › Article › peer-review

119 Citations (Scopus)

Abstract

The Explainable Expert Systems framework (EES), in which the focus is on capturing those design aspects that are important for producing good explanations, including justifications of the system's actions, explications of general problem-solving strategies, and descriptions of the system's terminology, is discussed. EES was developed as part of the Strategic Computing Initiative of the US Dept. of Defense's Defense Advanced Research Projects Agency (DARPA). Both the general principles from which the system was derived and how the system was derived from those principles can be represented in EES. The Program Enhancement Advisor, which is the main prototype on which the explanation work has been developed and tested, is presented. PEA is an advice system that helps users improve their Common Lisp programs by recommending transformations that enhance the user's code. How EES produces better explanations is shown.

Original language	English
Pages (from-to)	58-64
Number of pages	7
Journal	IEEE Expert
Volume	6
Issue number	3
DOIs	https://doi.org/10.1109/64.87686
Publication status	Published - Jun 1991

Access to Document

10.1109/64.87686

Cite this

@article{d38b1939c353460f9b71269c0925317f,

title = "Explanations in knowledge systems: Design for Explainable Expert Systems",

abstract = "The Explainable Expert Systems framework (EES), in which the focus is on capturing those design aspects that are important for producing good explanations, including justifications of the system's actions, explications of general problem-solving strategies, and descriptions of the system's terminology, is discussed. EES was developed as part of the Strategic Computing Initiative of the US Dept. of Defense's Defense Advanced Research Projects Agency (DARPA). Both the general principles from which the system was derived and how the system was derived from those principles can be represented in EES. The Program Enhancement Advisor, which is the main prototype on which the explanation work has been developed and tested, is presented. PEA is an advice system that helps users improve their Common Lisp programs by recommending transformations that enhance the user's code. How EES produces better explanations is shown.",

author = "William Swartout and C{\'e}cile Paris and Johanna Moore",

year = "1991",

month = jun,

doi = "10.1109/64.87686",

language = "English",

volume = "6",

pages = "58--64",

journal = "IEEE Expert",

issn = "0885-9000",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "3",

}

TY - JOUR

T1 - Explanations in knowledge systems

T2 - Design for Explainable Expert Systems

AU - Swartout, William

AU - Paris, Cécile

AU - Moore, Johanna

PY - 1991/6

Y1 - 1991/6

N2 - The Explainable Expert Systems framework (EES), in which the focus is on capturing those design aspects that are important for producing good explanations, including justifications of the system's actions, explications of general problem-solving strategies, and descriptions of the system's terminology, is discussed. EES was developed as part of the Strategic Computing Initiative of the US Dept. of Defense's Defense Advanced Research Projects Agency (DARPA). Both the general principles from which the system was derived and how the system was derived from those principles can be represented in EES. The Program Enhancement Advisor, which is the main prototype on which the explanation work has been developed and tested, is presented. PEA is an advice system that helps users improve their Common Lisp programs by recommending transformations that enhance the user's code. How EES produces better explanations is shown.

AB - The Explainable Expert Systems framework (EES), in which the focus is on capturing those design aspects that are important for producing good explanations, including justifications of the system's actions, explications of general problem-solving strategies, and descriptions of the system's terminology, is discussed. EES was developed as part of the Strategic Computing Initiative of the US Dept. of Defense's Defense Advanced Research Projects Agency (DARPA). Both the general principles from which the system was derived and how the system was derived from those principles can be represented in EES. The Program Enhancement Advisor, which is the main prototype on which the explanation work has been developed and tested, is presented. PEA is an advice system that helps users improve their Common Lisp programs by recommending transformations that enhance the user's code. How EES produces better explanations is shown.

UR - http://www.scopus.com/inward/record.url?scp=0026169418&partnerID=8YFLogxK

U2 - 10.1109/64.87686

DO - 10.1109/64.87686

M3 - Article

AN - SCOPUS:0026169418

SN - 0885-9000

VL - 6

SP - 58

EP - 64

JO - IEEE Expert

JF - IEEE Expert

IS - 3

ER -

Explanations in knowledge systems: Design for Explainable Expert Systems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this