Publication Abstract Title The automated generation of Web documents that are tailored to the individual reader Authors Chrysanne DiMarco and Mary Ellen Foster Abstract Many studies in communication have shown that presenting information in a manner that is tailored to the characteristics of a particular audience can have a profound effect on an individual. Incorporating this kind of tailoring facility in a system for the management and presentation of Web documents would be a very significant 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 developing Web-based natural language generation systems that can tailor documents to the individual user on demand. Full paper Postscript 5.4 mb