An argument-based framework for selecting dialogue move types and content

Mark Snaith (Lead / Corresponding author)

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Downloads (Pure)

Abstract

Choosing what to say is an integral part of multi-party dialogue, whether to ensure a natural flow, or advance a strategy. This paper presents an argument-based framework for selecting dialogue move types and content. The framework first builds and evaluates arguments in favour of move types and content being preferred, before determining whether or not there is an optimal outcome-where both the move type and content are preferred-or a sub-optimal outcome-where either the type or content is preferred, but not both.

Original languageEnglish
Title of host publicationComputational Models of Argument
Subtitle of host publicationProceedings of COMMA 2020
EditorsHenry Prakken, Stefano Bistarelli, Francesco Santini, Carlo Taticchi
Place of PublicationAmsterdam
Pages355-362
Number of pages8
ISBN (Electronic)9781643681078
DOIs
Publication statusPublished - 2020
Event8th International Conference on Computational Models of Argument, COMMA 2020 - Virtual, Online, Italy
Duration: 8 Sep 202011 Sep 2020

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume326
ISSN (Print)0922-6389

Conference

Conference8th International Conference on Computational Models of Argument, COMMA 2020
CountryItaly
CityVirtual, Online
Period8/09/2011/09/20

Keywords

  • Argumentation
  • Dialogue
  • Dialogue move selection
  • Strategies

Cite this