Simon Wells
Reconsidering RepStat rules in dialectic games.
Wells, Simon; Snaith, Mark
Authors
Dr Mark Snaith m.snaith@rgu.ac.uk
Lecturer
Contributors
Floriana Grasso
Editor
Nancy L. Green
Editor
Jodi Schneider
Editor
Simon Wells
Editor
Abstract
Prohibition of repeated statements has benefits for the tractability and predictability of dialogues carried out by machines, but doesn't match the real world behaviour of people. This gap between human and machine behaviour leads to problems when formal dialectical systems are applied in conversational AI contexts. However, the problem of handling statement repetition gives insight into wider issues that stem partly from the historical focus on formal dialectics to the near exclusion of descriptive dialectics. In this paper we consider the problem of balancing the needs of machines versus those of human participants through the consideration of both descriptive and formal dialectics integrated within a single overarching dialectical system. We describe how this approach can be supported through minimal extension of the Dialogue Game Description Language.
Citation
WELLS, S. and SNAITH, M. 2022. Reconsidering RepStat rules in dialectical games. In Grasso, F., Green, N.L., Schneider, J. and Wells, S. (eds.) Computational models of natural argument (CMNA 2022): proceedings of the 22nd workshop on Computational models of natural argument 2022 (CMNA 2022), 12 September 2022, Cardiff, UK. CEUR workshop proceedings, 3205. Aachen: CEUR-WS [online], pages 18-28. Available from: http://ceur-ws.org/Vol-3205/paper3.pdf
Conference Name | 22nd Workshop Computational models of natural argument 2022 (CMNA 2022) |
---|---|
Conference Location | Cardiff, UK |
Start Date | Sep 12, 2022 |
Acceptance Date | Aug 5, 2022 |
Online Publication Date | Sep 12, 2022 |
Publication Date | Sep 7, 2022 |
Deposit Date | Oct 6, 2022 |
Publicly Available Date | Oct 6, 2022 |
Publisher | CEUR Workshop Proceedings |
Pages | 18-28 |
Series Title | CEUR workshop proceedings |
Series Number | 3205 |
Series ISSN | 1613-0073 |
Book Title | Computational models of natural argument (CMNA 2022): proceedings of the 22nd workshop on Computational models of natural argument 2022 (CMNA 2022), 12 September 2022, Cardiff, UK |
Keywords | Human behaviour; Machine behaviour; Dialectical games; Argumentation-based dialogue; RepStat rules; Repetition |
Public URL | https://rgu-repository.worktribe.com/output/1769590 |
Publisher URL | http://ceur-ws.org/Vol-3205/ |
Files
WELLS 2022 Reconsidering RepStat rules (VOR)
(274 Kb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by/4.0/
Copyright Statement
You might also like
Agents United: an open platform for multi-agent conversational systems.
(2021)
Conference Proceeding
Towards a declarative approach to constructing dialogue games.
(2021)
Conference Proceeding
Debating technology for dialogical argument: sensemaking, engagement, and analytics.
(2017)
Journal Article