Text Generation in a Dynamic Hypertext Environment

Maria Milosavljevic, Adrian Tulloch and Robert Dale
Microsoft Institute and Macquarie University,
65 Epping Road, North Ryde NSW, Australia.
{t-mariam, t-atullo, rdale}@microsoft.com

Abstract

This paper describes PEBA-II, a working natural language generation system which interactively describes animals in a taxonomic knowledge base via the production of World Wide Web pages. Our aim is to construct a natural language document generation system with real practical applicability: to this end, the system reconstructs and combines a number of existing ideas in the literature in a novel way, and proposes a solution to the problem of breadth of coverage that is based on a pragmatic approach to knowledge representation and linguistic realisation. The system embodies the following features:

a reconstruction of some of the core ideas in schema--based text generation [McKeown 1985], applied to the generation of hypertext documents;
the principled use of a phrasal lexicon to ease surface generation, in concert with a knowledge base whose elements may correspond to pre--compiled collections of atomic units;
a user model and discourse model that permit interesting variations in the texts produced.

We describe each of the above aspects of the existing system in some detail, and point to a number of interesting research directions it opens up.

Conference Home Page