Detecting and Responding to Plan-Oriented Misconceptions

Abstract

This paper discusses the problem of recognizing and responding to plan-oriented misconceptions in advice-seeking dialogs, concentrating on the problems of novice computer users. A cooperative response is one that not only corrects the user's mistaken belief, but also addresses the missing or mistaken user beliefs that led to it. Responding appropriately to a potentially incorrect user belief is presented as a process of 1. checking whether the advisor holds the user's belief; 2. confirming the belief as a misconception by finding an explanation for why the advisor does not hold this belief; 3. detecting the mistaken beliefs underlying the misconception by trying to explain why the user holds the incorrect belief, and 4. providing these explanations to the user. An explanation is shown to correspond to a set of advisor beliefs, and searching for an explanation to proving whether various abstract configurations of advisor beliefs hold. A taxonomy of domain-independent explanations for potential user misconceptions involving plan applicability conditions, preconditions, and effects is presented. INTRODUCTIONA novice computer user having trouble performing a task often describes his problem to an expert, who is then expected to explain its cause and provide its solution. Consider, for example, the following adviceseeking dialog between a novice UNIX user and his more experienced counterpart.User: I tried to remove a file with the "rm" command. But the file was not removed and the error message was permission denied. I checked and I own the file. What's wrong? Advisor: To remove a file, you need to be able to write into the directory containing it. You do not need to own the file. User: How do I make that directory writeable? Advisor: To make a directory writeable, use the "chmod +w" command. User: Wait a second while I try it. No, "chmod +w" prints the error message "permission denied". Advisor: To make a directory writeable, you need to own it. User: So to remove a file, I have to own the directory that contains it.Advisor: No, to remove a file, you need to have write permission on the directory that contains it. You do not need to own the directory that contains it. You need to own that directory when you do not already have write permission on it. User: So how do I remove the file? Advisor: Send mail to whomever has write permission on the directory, asking him to remove the file for you. Participating as the advisor in such a dialog requires the ability to recognize and respond to missing or mistaken user beliefs about plan applicability conditions, preconditions, and effects. The advisor above recognizes two user misconceptions. The user first incorrectly believes that owning a file is a precondition to removing it, and then incorrectly believes that the precondition is owning the directory containing it. This advisor also notices several gaps in the user's knowledge. The user has no plan for making a directory writeable, does not know why the advisor's plan for doing so failed, and has no plan for removing a fi...

Plan Realization for Complex Command Interaction in the UNIX Help Domain

“…This approach has been strongly promoted in the domain of providing expert medical advice (Miller, 1984). However it is also central to several operating system help systems, including Wizard (Finin, 1983) and AQUA (Quilici et al, 1988). In such systems, a user's attempt at solving a simple problem (such as deleting a group of files) is observed, and a "better" approach is suggested by the system.…”

Plan Authoring Based on Sketches, Advice and Templates

“…However, there have been some notable attempts to address the problem of recognition of faulty plans. Classifications of different types of plan-based misconceptions are presented in [Pollack 1986, Quilici et al 1988, van Beek et al 1993, with a comprehensive and detailed list provided in [Calistri-Yeh 1991]. The emphasis in that work is on identifying user misconceptions, with no consideration given to potential problems in the underlying domain knowledge.…”

Untitled

“…For example, by inferring an underlying plan motivating a user's utterances, a system can anticipate obstacles that might prevent the user from successfully executing his/her plan, and provide augmented responses to remove these obstacles . In addition to using plan recognition to supply more information than explicitly requested , plan recognition has formed the basis of systems that understand indirect speech acts ), respond to ill-formed queries (Carberry, 1988), detect and correct misconceptions (Quilici, 1989), handle queries based on invalid plans (Pollack, 1990), and recognize complex discourse acts such as expressions of doubt (Carberry and Lambert, 1999). Plan-based reasoning has also provided new methodologies for handling traditional linguistic phenomena, such as resolving referring expressions (Grosz, 1977) and inter-sentential ellipsis (Carberry, 1985;Litman, 1986).…”