Incorporating User Models into Expert Systems for Educational Diagnosis

Cohen, Robin; Jones, Marlene

doi:10.1007/978-3-642-83230-7_11

Cited by 17 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of course if the patient and agent are identical, the system has a richer model to support its interaction with the user in his agent role. A system may have independent agent stereotypes which can influence output as in Cohen and Jones 1989, where explanations about the patient's educational performance are tailored to types of agent. (In Paris 1989 the choice of explanation is rather different as it can be viewed as a system decision for the patient user who is also the agent.)…”

Section: Generationmentioning

confidence: 99%

Tailoring output to the user: What does user modelling in generation mean?

Jones¹

1991

The Kluwer International Series in Engineering and Computer Science

View full text Add to dashboard Cite

Section: Generationmentioning

confidence: 99%

Tailoring output to the user: What does user modelling in generation mean?

Jones¹

1991

The Kluwer International Series in Engineering and Computer Science

View full text Add to dashboard Cite

“…An actual system with explicit models for both agent and patient is the CGD system for educational diano. [3] However, although this system sometimes talks about the patient, it never communicates with with the patient. Wahlster's HAM-ANS system for hotel reservations [17, page 953] models the patient for communication, but does not explicitly model the agent.…”

Section: Introductionmentioning

confidence: 99%

Modeling all dialogue system participants to generate empathetic responses

Haimowitz¹

1991

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

“…A constraint of the second type is a query about whether the user belongs to a specific stereotype, e.g., (ISA USER SYSTEM-DEVELOPER). This type of constraint is useful because certain explanation strategies are appropriate for some types of users and not others (Paris, 1988;Cohen and Jones, 1989). For example, the system may have two strategies available for justifying a conclusion: one which closely traces the reasoning of the expert system, and one that summarizes it by highlighting the main points.…”

Section: Checking Constraints and Making Assumptionsmentioning

confidence: 99%

Exploiting user feedback to compensate for the unreliability of user models

Moore

Paris²

1992

User Model User-Adap Inter

View full text Add to dashboard Cite

Abstract. Natural Language is apowerful medium for interacting with users, and sophisticated computer systems using natural language are becoming more prevalent. Just as human speakers show an essential, inbuilt responsiveness to their hearers, computer systems must "tailor" their utterances to users. Recognizing this, researchers devised user models and strategies for exploiting them in order to enable systems to produce the "best" answer for a particular user. and her bachelor's degree from the University of California in Berkeley. Her research interests include natural language generation and user modeling, discourse, expert system explanation, human-computer interaction, intelligent tutoring systems, machine learning, and knowledge acquisition. At Columbia University, she developed a natural language generation system capable of producing multi-sentential texts tailored to the users" level of expertise about the domain. At ISI, she has been involved in designing a flexible explanation facility that supports dialogue for an expert system shell. Because these efforts were largely devoted to investigating how a user model could be exploited to produce better responses, systems employing them typically assumed that a detailed and correct model of the user was available a priori, and that the information needed to generate appropriate responses was included in that model. However, in practice, the completeness and accuracy of a user model cannot be guaranteed. Thus, unless systems can compensate for incorrect or incomplete user models, the impracticality of building user models will prevent much of the work on tailoring from being successfully applied in real systems. In this paper, we argue that one way for a system to compensate for an unreliable user model is to be able to react to feedback from users about the suitability of the texts it produces. We also discuss how such a capability can actually alleviate some of the burden now placed on user modeling. F~inally, we present a text generation system that employs whatever information is available in its user model in an attempt to produce satisfactory texts, but is also capable of responding to the user's follow-up questions about the texts it produces.

show abstract

Incorporating User Models into Expert Systems for Educational Diagnosis

Cited by 17 publications

References 10 publications

Tailoring output to the user: What does user modelling in generation mean?

Tailoring output to the user: What does user modelling in generation mean?

Modeling all dialogue system participants to generate empathetic responses

Exploiting user feedback to compensate for the unreliability of user models

Contact Info

Product

Resources

About