Abstract

Although the late binding of form is now commonplace in structured document preparation systems, a similar delay in the binding of content is necessary to achieve user-tailored interaction. The authoring paradigm we have developed to service this goal is called intent-based authoring, because the author supplies at compile-time a communicative goal, or intent. Just as SGML editors and HTML browsers defer rendering decisions until run-time by referring to a local style-sheet, intent-based authoring systems defer content-slection decisions until run-time when they refer to models of both author and reader(s).

This thesis shows that techniques from artificial intelligence can be developed and used to acquire, represent and exploit such models. Probalistic abduction is used to recognize user models, and cost-based abduction to design tailored presentations. These techniques are combined in a single framework for best-first recognition and design.

These reasoning techniques are further allied with an interaction paradigm we call scrutability, whereby users critique the model in pursuit of better presentations, users see a critical subset of the model determined by sensitivity analysis and can change values through a graphical user interface. The interactivity is modelled to ensure that representations of the user model to the user are made in the most perceptually salient manner.

A prototype for intent-based video authoring is described. Video is used as a test medium because it is a "worst case" temporally linear medium; a viable solution to video authoring problems should apply easily to more tractable traditional media.

The primary contribution of this dissertation is to the field of applied artificial intelligence, specifically to the emerging field of user modelling. The central contribution is the intent-based authoring framework for separataing intent from content.

@PhdThesis{Csinger1996,
	author = {Andrew Scinger, Ph.D},
	title = {User Models for Intent-Based Authoring},
	school = {UBC},
	year = {1996},
	supervisor = {Kellogg S. Booth and David Poole},
}