The application of rhetorical structure theory to interactive news program generation from digital archives

Rhetorical structure theory (RST) provides a model of textual function based upon rhetoric. Initially developed as a model of text coherence, RST has been used extensively in text generation research, and has more recently been proposed as a basis for multimedia presentation generation. This paper investigates the use of RST for generating video presentations having a rhetorical form, using models of the rhetorical roles of video components, together with rules for selecting components for presentation on the basis of their rhetorical functions. An RST model can provide a predefined link structure providing viewers with options for obtaining and dynamically modifying rhetorically coherent video presentations from video archives and databases. The use of an RST analysis for interactive presentation generation may provide a more powerful rhetorical device than conventional linear video presentation. Conversely, making alternative RST analyses of the same video data available to users can have the effect of encouraging closer and more independent viewer analysis of the material, and discourage taking any particular rhetorical presentation at face value.