J. Boose, "ETS: A System for the Transfer of Human Expertise", in Knowledge Based Problem Solving, Prentice Hall, 1986, pp. 68-111.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Other problems relate to the nature of experts. For example, experts do not introspect reliably. MUSE89] Experts are usually bad at explaining, but good at doing. CHOR90] Experts have difficulty articulating problem solving knowledge in a form suited for representation in an expert system. [BOOS86] For these reasons, the domain analyst must find an expert who can, and who is willing to, spend a few hours exploring a domain, and who can be on call while the elicited knowledge is encoded in an expert system and then tested. CHOR90] 44 Even more fundamental problems face the domain analyst ....

....directly with a domain expert to create an expert system for a specific domain. One such system, the 50 Expertise Transfer System (ETS) reported by Boose, attempts to cut the time required (typically six to 24 months depending on the domain) to create an expert system using interview techniques. [BOOS86] ETS employs clinical psychotherapeutic interviewing methods, called Personal Construct Theory, originally developed by George Kelly. KELL55] ETS automatically interviews an expert, analyzes the information gathered, and then generates a set of production rules. ETS incorporates an inference ....

J. Boose, "ETS: A System for the Transfer of Human Expertise", in Knowledge Based Problem Solving, Prentice Hall, 1986, pp. 68-111.

....1988) Like the approach of Tecuci (1995) The Knowledge Factory is distinguished by being designed for direct use by experts with minimal training or experience in knowledge engineering. The system also differs 7 from a number of knowledge elicitation systems designed for direct use by experts (Boose, 1986; Compton, Edwards, Srinivasan, Malor, Preston, Kang, Lazarus, 1992) not only by the provision of machine learning facilities, but also by not relying upon the expert to give suitable solutions for all cases that are encountered. The Knowledge Factory employs simple knowledge representation ....

Boose, J. H. (1986). ETS: A system for the transfer of human expertise. In J. S. Kowalik (Ed.), Knowledge based problem solving. New York: Prentice-Hall.

....accumulate a suitable set of example cases. It can be seen that this type of situation lies between standard machine learning, previous approaches to integrating machine learning with knowledge elicitation and automated knowledge elicitation aids such as ripple down rules [12] and repertory grids [13] . It is distinguished from standard machine learning by the tight integration of the domain expert into the knowledge acquisition process. It is distinguished from previous approaches to integrating machine learning with knowledge elicitation by removing the knowledge engineer from the process. ....

J. H. Boose, ETS: A system for the transfer of human expertise, in: J. S. Kowalik, ed. Knowledge Based Problem Solving (Prentice-Hall, New York, 1986).

....Wilkins, 1988) Like the approach of Tecuci (1995) the Knowledge Factory is distinguished by being designed for direct use by experts with minimal knowledge engineering training or experience. It is distinguished from a number of knowledge elicitation systems designed for direct use by experts (Boose, 1986; Compton, Edwards, Srinivasan, Malor, Preston, Kang, Lazarus, 1992) not only by the provision of machine learning facilities, but also by not relying upon the expert to be able to provide suitable solutions to all tasks. The Knowledge Factory is distinguished from the approach of Tecuci (1995) ....

Boose, J. H. (1986). ETS: A system for the transfer of human expertise. In J. S. Kowalik (Ed.), Knowledge based problem solving. New York: Prentice-Hall.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC