Electronic hypertext catalogues provide an important channel for information provision. However, static hypertext documents cannot be dynamically adapted to help the user find what he/she is looking for. We demonstrate that natural language generation techniques can be used to produce tailored hypertext documents, and we focus on two key benefits of the resulting DYNAMIC HYPERTEXT. First, documents can be tailored more precisely to an individual's needs and background, thus aiding the search process. Secondly, the incorporation of techniques for comparing catalogue items allows the user to search still more effectively. We describe the automatic generation of hypertext documents containing comparisons, with illustrations from two implemented systems. KEYWORDS: adaptive hypertext, dynamic hypertext, natural language generation, user modelling, discourse history INTRODUCTION The advent of on-line distributed hypertext systems and the world wide web (WWW) has led to the extensive popul...

We outline experience with the Intelligent Labelling Explorer, a dynamic hypertext system developed at the University of Edinburgh, in collaboration with the National Museums of Scotland. First, we indicate a number of ways in which labels on museum objects ought to be tuned to take into account types of visit, the interests of visitors, and their evolving knowledge during a visit. Secondly, we sketch the general architecture of our system, and then focus on the conversational effects which the system can create. We then briefly indicate future directions of research, before critically discussing the applicability (or otherwise) of the spatial metaphor to flexible hypertexts. Keywords: adaptive museum hypermedia, natural language techniques for dynamic hypertext generation, content adaptation in hypertext and hypermedia, web-based museum hypermedia, navigation design 1. Introduction We take dynamic hypertext to be that variety of flexible hypertext which relies upon techniques from th...

In this paper, we discuss an approach that tries to blur the distinction between adaptive hypermedia and dynamic hypermedia. The approach aims at finding an optimal trade-off between resource reuse and flexibility: existing atomic pieces of data are collected and properly annotated; at the interaction time, the system dynamically builds the nodes of the hypermedia composing different pieces together. The proposed annotation formalism is illustrated and a rule-based system to compose hypermedia nodes exploiting different knowledge sources is presented. Finally, the advantages of this approach with respect to adaptation and dynamic generation are discussed.

Multimedia systems—systems which employ several media such as text, graphics, animation and sound for the presentation of information—have become widely available during the last decade. The acceptance and usability of such systems is, however, substantially affected by their limited ability to present information in a flexible manner. As the need for flexibity grows, the manual creation of multimedia presentations becomes less and less feasible. While the automatic production of material for presentation is rarely addressed in the multimedia community, a considerable amount of research effort has been directed towards the automatic generation of natural language. The purpose of this chapter is to introduce techniques for the automatic production of multimedia presentations; these techniques draw upon lessons learned during the development of natural language generators.

We present an experiment for designing a logic based QA system, WEBCOOP, that integrates knowledge representation and advanced reasoning procedures to generate cooperative responses to natural language queries on the web. The system is first developed for the tourism domain. We then examine how and under what conditions this system can be re-used for other domains. 1

This paper describes Te Kaitito, a system for natural language processing in English and Maori. The paper focusses on the high-level architecture of the system, and the design decisions which motivate this architecture. An example of an interaction with the system is also given.

Interaction with an adaptive hypertext can be seen as a form of "goal-oriented" dialogue, where the user asks for information through a set of predefined queries and the system answers ensuring that the global communicative goal of the information process is achieved through a sequence of dialogue sections (hypermedia nodes). The system establishes what to say to the user at every turn of the dialogue based on the user model settings and on the interaction history. Planning on demand the information content of a hypertext node that responds to a particular link selection in a particular context requires a 'reactive' approach; this differs from common hypertext planning in that it applies local adjustment criteria to an overall plan and, in mixed-initiative situations, tries to fit together the system's and the user's points of view. Keywords Dynamic hypertext generation, mixed-initiative interaction, automated presentation of information. INTRODUCTION Plan-based approaches to deep ...

We outline experience with the Intelligent Labelling Explorer, a dynamic hypertext system developed at the University of Edinburgh, in collaboration with the National Museums of Scotland. First, we indicate a number of ways in which labels on museum objects ought to be tuned to take into account types of visit, the interests of visitors, and their evolving knowledge during a visit. Secondly, we sketch the general architecture of our system, and then focus on the conversational effects which the system can create. We then briefly indicate future directions of research, before critically discussing the applicability (or otherwise) of the spatial metaphor to flexible hypertexts.

Abstract not found