Proceedings of ALTSS/ALTW, Melbourne, December 2003
In this series of two lectures we will look at what is involved in getting a computer to plan the content of a text.
Lecture 1:
Text Planning in the Large: Discourse Structure
We introduce the architecture of natural language generation systems, identifying the key components and the information they use. We focus in on the task of taking a body of content to be expressed and organising this into a coherent discourse, and examine a number of different approaches that have been taken to the structural organisation of text.
Lecture 2:
Text Planning in the Small: Referring Expressions
Natural language generation systems not only need to plan how to organise the body of information they want to express into coherent paragraphs. They also need to reason about the detail within individual sentences, and nowhere is this more evident than in the generation of referring expressions. Here the need is to determine how to refer to entities and sets in the domain of discourse so that the hearer knows what is being talked about.
Professor Robert Dale is Director of the Centre for Language Technology at Macquarie University in Sydney, where he teaches on various aspects of language technology. After completing his PhD in Computational Linguistics at the University of Edinburgh in 1989, he taught in the Centre for Cognitive Science at Edinburgh, before taking up a position with Microsoft in Sydney in 1994. He was Director of the Microsoft Research Institute at Macquarie University (1996-1999). His research interests include intelligent text processing; natural language generation; spoken language dialog systems; and reference and anaphora. He is author or editor of five books and around 60 papers in various aspects of natural language processing, and is editor of the Journal of Computational Linguistics. [http://www.ics.mq.edu.au/~rdale/]