The Automated Generation of Web Documents that Are Tailored to the Individual Reader

Chrysanne DiMarco and Mary Ellen Foster

Many studies in communication have shown that presenting information in amanner that is tailored to the characteristics of a particular audience can have a significant effect on an individual. Incorporating this kind of tailoring facility in a systemfor themanagement and presentation ofWeb documents would be a very important enhancement of the Web’s current state of development. Our long-term research goal has been to investigate and develop theories of text composition, in particular, computational models of rhetorical structure and lexical semantics, which are particular problems for incorporating style in natural language systems. Recently, we have begun to apply this research to developingWeb-based natural language generation systems that can tailor documents to the individual user on demand.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.