麻豆AV

Explanation, Semantics and Ontology in the Design of Trustworthy Cyber-Human Systems

By Giancarlo Guizzardi

University of Twente

Date: January 8, 2025
Time: 11:00 AM to 1:00 PM

View poster

听

Abstract

Cyber-human systems are formed by the coordinated interaction of human and computational components. The latter are justified to the extent that they are meaningful to humans 鈥� in both senses of 鈥榤eaning鈥�, i.e., in the sense of semantics as well as in the sense of purpose or significance. On one hand, the data these components manipulate only acquire meaning when mapped to shared human conceptualizations of the world. On the other hand, they can only be justified if ethically designed. Cyber-human systems are trustworthy if the interoperation of their components is meaning preserving, i.e., if we are able to semantically interoperate these components; and transparently demonstrate (i.e., explain) how their interoperation positively contributes to human values and goals. In this talk, I will present a notion of explanation termed Ontological Unpacking, which aims at explaining symbolic domain descriptions (conceptual models, knowledge graphs, logical specifications). I show that it is this explanatory nature that is required for semantic interoperability and, hence, trustworthiness. Finally, I will argue that the current trend in XAI (Explainable AI) in which 鈥渢o explain is to produce a symbolic artifact鈥� is an incomplete project as these artifacts are not 鈥渋nherently interpretable鈥�, and that they should be taken as the beginning of the road to explanation, not the end.