Why Should I Turn Left? Towards Active Explainability for Spoken Dialogue Systems.

Vladislav Maraev, Ellen Breitholtz, Christine Howes, Jean-Philippe Bernardy


Abstract
In this paper we argue that to make dialogue systems able to actively explain their decisions they can make use of enthymematic reasoning. We motivate why this is an appropriate strategy and integrate it within our own proof-theoretic dialogue manager framework based on linear logic. In particular, this enables a dialogue system to provide reasonable answers to why-questions that query information previously given by the system.
Anthology ID:
2021.reinact-1.9
Volume:
Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)
Month:
October
Year:
2021
Address:
Gothenburg, Sweden
Venue:
ReInAct
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–64
Language:
URL:
https://aclanthology.org/2021.reinact-1.9
DOI:
Bibkey:
Cite (ACL):
Vladislav Maraev, Ellen Breitholtz, Christine Howes, and Jean-Philippe Bernardy. 2021. Why Should I Turn Left? Towards Active Explainability for Spoken Dialogue Systems.. In Proceedings of the Reasoning and Interaction Conference (ReInAct 2021), pages 58–64, Gothenburg, Sweden. Association for Computational Linguistics.
Cite (Informal):
Why Should I Turn Left? Towards Active Explainability for Spoken Dialogue Systems. (Maraev et al., ReInAct 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.reinact-1.9.pdf