Modelling control in generation

Roger Evans, David Weir, John Carroll, Daniel Paiva, Anja Belz

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

Abstract

In this paper we present a view of natural language generation in which the control structure of the generator is clearly separated from the content decisions made during generation, allowing us to explore and compare different control strategies in a systematic way. Our approach factors control into two components, a ‘generation tree’ which maps out the relationships between different decisions, and an algorithm for traversing such a tree which determines which choices are actually made. We illustrate the approach with examples of stylistic control and automatic text revision using both generative and empirical techniques. We argue that this approach provides a useful basis for the theoretical study of control in generation, and a framework for implementing generators with a range of control strategies. We also suggest that this approach can be developed into tool for analysing and adapting control aspects of other advanced wide-coverage generation systems.
Original languageEnglish
Title of host publication11th European Workshop on Natural Language Generation (ENLG '07)
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages25-32
Number of pages8
DOIs
Publication statusPublished - 1 Jun 2007
Event11th European Workshop on Natural Language Generation (ENLG '07) - Schloss Dagstuhl, Germany
Duration: 1 Jun 2007 → …

Workshop

Workshop11th European Workshop on Natural Language Generation (ENLG '07)
Period1/06/07 → …

Keywords

  • Natural language generation

Cite this