Cookies

We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.


Durham e-Theses
You are in:

Dialogue structure models: an engineering approach to machine analysis and generation of dialogue

Jones, Cerian E. (1994) Dialogue structure models: an engineering approach to machine analysis and generation of dialogue. Doctoral thesis, Durham University.

[img]
Preview
PDF
4Mb

Abstract

The problem area addressed within this research is the processing and understanding of natural English dialogue by computer. The presented work fundamentally constitutes the development of a theory for modelling natural dialogue, and the practical implementation of that theory. There are two major aspects of consideration within the theory: the modelling of dialogue structure is balanced against certain individual factors. The structure of the dialogue is modelled via the mechanism of the Dialogue Structure Models and its constituent parts, accounting for situational context, participant motivation, participant role(s) and other contributory factors. The individual factors, on the other hand, are peculiar to the dialogue currently in progress, and cannot be pre-determined in the way that structure can. These factors include:1. The personal characteristics of the participants (their personalities, backgrounds, interests and belief systems); 2. The overall mood of the participant (how (s)he is feeling today; the emotional state of the participant); 3. Instantiation factors relating to the events and circumstances of the particular dialogue in progress. (For example, how a participant reacts intellectually or emotionally to what the other person has just said).A description of the implementation of this theory is presented, followed by a discussion of the testing techniques used to ensure that the original criteria for success have been met.

Item Type:Thesis (Doctoral)
Award:Doctor of Philosophy
Thesis Date:1994
Copyright:Copyright of this thesis is held by the author
Deposited On:16 Nov 2012 11:00

Social bookmarking: del.icio.usConnoteaBibSonomyCiteULikeFacebookTwitter