arXiv Analytics

Sign in

arXiv:2108.13766 [cs.CL]AbstractReferencesReviewsResources

The five Is: Key principles for interpretable and safe conversational AI

Mattias Wahde, Marco Virgolin

Published 2021-08-31Version 1

In this position paper, we present five key principles, namely interpretability, inherent capability to explain, independent data, interactive learning, and inquisitiveness, for the development of conversational AI that, unlike the currently popular black box approaches, is transparent and accountable. At present, there is a growing concern with the use of black box statistical language models: While displaying impressive average performance, such systems are also prone to occasional spectacular failures, for which there is no clear remedy. In an effort to initiate a discussion on possible alternatives, we outline and exemplify how our five principles enable the development of conversational AI systems that are transparent and thus safer for use. We also present some of the challenges inherent in the implementation of those principles.

Related articles: Most relevant | Search more
arXiv:2001.10929 [cs.CL] (Published 2020-01-29)
AMR Similarity Metrics from Principles
arXiv:1407.7169 [cs.CL] (Published 2014-07-26)
Principles and Parameters: a coding theory perspective
arXiv:1808.02022 [cs.CL] (Published 2018-08-06)
Principles for Developing a Knowledge Graph of InterlinkedEvents from News Headlines on Twitter