DocumentCode :
2862099
Title :
Providing expert advice by analogy for on-line help
Author :
Lieberman, Henry ; Kumar, Ashwani
Author_Institution :
Media Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
fYear :
2005
fDate :
19-22 Sept. 2005
Firstpage :
26
Lastpage :
32
Abstract :
One of the principal problems of online help is the mismatch between the specialized knowledge and technical vocabulary of experts who are providing the help, and the relative naivete of novices, who usually are often not in a position to understand solutions expressed by the expert in their own terms. Most of the interfaces are plagued by recurrent key problems: 1) elicitation - how to ask questions that enable the helper to make decisions, and at the same time, are understandable to the novice, and 2) explanation - how to explain rationale behind expert decisions in terms that the user can understand. One of the best ways to do this is for the expert to provide analogies in terms of Commonsense knowledge, which provide metaphors that help novices learn problem-solving skills. SuggestDesk is a system that acts as an advisor to an online technical support person. It uses a large Commonsense knowledge base to search for analogies between known technical problem-solution pairs, and situations and events in everyday life that can be used to explain them.
Keywords :
common-sense reasoning; expert systems; problem solving; technical support services; Commonsense knowledge; SuggestDesk system; expert advice; online help; Databases; Documentation; HTML; Humans; Laboratories; Personnel; Problem-solving; Real time systems; Telephony; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Agent Technology, IEEE/WIC/ACM International Conference on
Print_ISBN :
0-7695-2416-8
Type :
conf
DOI :
10.1109/IAT.2005.120
Filename :
1565506
Link To Document :
بازگشت