This talk will present the case for abstract document structure as a separate descriptive level in the analysis and generation of written texts. The purpose of this representation is to mediate between the message of a text (i.e., its discourse structure) and its physical presentation (i.e., its organization into graphical constituents like sections, paragraphs, sentences, bulleted lists, figures, footnotes and so forth). Abstract document structure can be seen as an extension of Nunberg's `text-grammar'; it is also closely related to `logical' mark-up in languages like HTML and LaTeX. I will argue that by using this intermediate representation, several subtasks in language generation and language understanding can be defined more cleanly, and demostrate this at work in the ICONOCLAST system, which generates a wide range of text (with layout) from a representation of the intended "message".
Professior Donia Scott is the Head of ITRI at the University of Brighton, UK. ITRI is a research department whose aim is to further interdisciplinary research on the interaction between people and computers, especially where natural language plays a role in this interaction. Her current research interests lie primarily in Artificial Intelligence and Natural Language Processing, especially Natural Language Generation and Discourse.