The design of illustrated documents as a planning task

Abstract

Not only the generation of text, but also the generation of multimodal documents can be considered as a sequence of communicative acts which aim to achieve certain goals. For the realization of a system able to automatically generate illustrated documents, a plan-based approach seems adequate. To represent knowledge about how to present information, we have designed presentation strategies which relate to both text and picture production. These strategies are considered as operators of a planning system. However, a conventional hierarchical planner for determining the contents and the rhetorical structure of a document has proven inappropriate to handle the various dependencies between content determination, mode selection and content realization. To overcome these problems, a new planning scheme has been developed that supports data transfer between the content planner and the mode-specific generation components and allows for revising an initial document structure.