Using conversation MOPs in natural language interfaces

Turner, Elise H.; Cullingford, Richard E.

doi:10.1080/01638538909544719

Cited by 17 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite reports of behavioral differences for persons with varying expectations of future interaction, information-seeking goals and information-revealing desires (Berger & Kellermann, 1983, the findings reported here suggest that these differences are ones of routine flexibility; the routines are being flexibly deployed to adapt to differing circumstances but the conversations are still routine, being structured quite similarly in their progression. This normative sequencing is most likely why MOP-based, advice-giving systems have been successfully developed on computer systems: The computer and the user share the same representation for the discourse structure (Cullingford & Kolodner, 1986;Turner & Cullingford, 1989a, 1989b, much as two persons must share similar structures for talk to progress easily. It seems to be the case that persons flexibly deploy routines within relatively invariant (and routine) sequential progression when conversing.…”

Section: Resultsmentioning

confidence: 99%

The Conversation MOP II. Progression Through Scenes in Discourse

Kellermann

1991

Human Comm Res

View full text Add to dashboard Cite

Based on previous research demonstrating that a conversation MOP (memory organization packet) exists that organizes Scenes (topics) in conversations, this research explores thegerreralizability of theMOP when faced with differing situational demands.This research tests a normative sequential progression claim of the MOP perspective by examining the degree to which the M O P permits routine progression in topical talk in initial interactions as acquaintance goals vary. As predicted, dyads having similar acquaintanceship goals were found to exhibit similar conversational structures; the conversational structures for dyads having differing acquaintanceship goals were also found to be similar; and the progression of dyads through conversations in terms of transitions between topics also exhibited structural invariance. It was therefore concluded that (a) certain topics of talk occur almost regardless of acquaintanceship desires despite idiosyncratic additions, (b) multiple topics of talk are appropriate at any given point but what is appropriate at one point is not appropriate at other points, and (c) conversational sequencing follows a normative progression. In other words, wnversational behavior is both routine and adaptive, although the adaptation is in itself routine.onversation is one of the most basic and fundamental means that persons use to become acquainted. It is rare for persons C to develop a relationship without ever conversing and even in such instances (e.g., pen pals, e-mail), a desire for conversation usually emerges. Conversations occurring in initial interactions are particularly critical for relationship development. For example, persons who disclose too much information too early during initial interactions tend to inhibit the very relationships they desire to develop (Berger, 1973). To make it easier for persons to negotiate initial interactions in relatively appropriate and efficient ways, conversational conventions and rituals are acquired and transmitted from one generation to the next. Meeting other people for the first time thus Kathy Kellermann is on the faculty of the Department of Communication at the University of California, Santa Barbara.

show abstract

Section: Resultsmentioning

confidence: 99%

The Conversation MOP II. Progression Through Scenes in Discourse

Kellermann

1991

Human Comm Res

View full text Add to dashboard Cite

show abstract

“…Other work on using context in real-world applications includes the work of Bre´zillon, Gentile, Saker and Secron (1997) on context's impact on problem-solving for subway incident handling; Guha and Lenat's (1990) work on common sense reasoning and Pinto, Stephens and Bonnell's (1995) work on geographic reasoning in Cyc; O ztu¨rk and Aamodt's (1997) work on medical diagnosis; E. Turner's (1989) work on conversational control; and Va´mos' (1995) work on modeling domain expert knowledge, which resulted in patterns similar to very simple contextual schemas.…”

Section: Related Workmentioning

confidence: 98%

Context-mediated behavior for intelligent agents

Turner¹

1998

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

“…Why should an inference based on a case, for example, be any different than one made based on a general plan derived from experience? It shouldn't (Martin, 1988;Shinn, 1988;Turner, 1988;Turner & Cullingford, 1989). One must still focus on a part of the plan.…”

Section: Control and Facilitation Of Case-based Inferencementioning

confidence: 99%

“…The MEDLATOR has processes that are consistent with such an architecture. And current research is addressing way to make these guidelines more concrete for real-world problems (e.g., Martin, 1988;Shhm, 1988;Turner, 1988;Turner & Cullingford, 1989).…”

Section: Control and Facilitation Of Case-based Inferencementioning

confidence: 99%

The MEDIATOR: Analysis of an Early Case‐Based Problem Solver⁴

1989

View full text Add to dashboard Cite

Case‐based reasoning is a reasoning method that capitalizes on previous experience. In case‐based reasoning, a new problem is solved in a way that is analogous to a previous similar problem. Case‐based reasoning can improve problem‐solving behavior in several ways: by providing reasoning shortcuts, by warning of the potential for error, and by suggesting a focus for reasoning. The MEDIATOR was one of the earliest case‐based, problem‐solving programs. Its domain is dispute resolution, and it uses case‐based reasoning for 10 different tasks involved in its problem solving. While some of the MEDIATOR's processes have been elaborated and improved on in later case‐based problem solvers, there remain many lessons that can be learned about case‐based reasoning by analyzing the MEDIATOR's behavior. This article provides a short description of the MEDIATOR and its domain, presents its successes and shortcomings, and analyzes the reasons why it behaves the way it does. As part of the analysis, the differences and similarities between the MEDIATOR and later case‐based reasoners are also described, as well as the implications of those differences.

show abstract

Using conversation MOPs in natural language interfaces

Cited by 17 publications

References 14 publications

The Conversation MOP II. Progression Through Scenes in Discourse

The Conversation MOP II. Progression Through Scenes in Discourse

Context-mediated behavior for intelligent agents

The MEDIATOR: Analysis of an Early Case‐Based Problem Solver⁴

Contact Info

Product

Resources

About

Using conversation MOPs in natural language interfaces

Cited by 17 publications

References 14 publications

The Conversation MOP II. Progression Through Scenes in Discourse

The Conversation MOP II. Progression Through Scenes in Discourse

Context-mediated behavior for intelligent agents

The MEDIATOR: Analysis of an Early Case‐Based Problem Solver4

Contact Info

Product

Resources

About

The MEDIATOR: Analysis of an Early Case‐Based Problem Solver⁴