Foundations of Explainable Knowledge-Enabled Systems
arXiv:2003.07520
Abstract
Explainability has been an important goal since the early days of Artificial Intelligence. Several approaches for producing explanations have been developed. However, many of these approaches were tightly coupled with the capabilities of the artificial intelligence systems at the time. With the proliferation of AI-enabled systems in sometimes critical settings, there is a need for them to be explainable to end-users and decision-makers. We present a historical overview of explainable artificial intelligence systems, with a focus on knowledge-enabled systems, spanning the expert systems, cognitive assistants, semantic applications, and machine learning domains. Additionally, borrowing from the strengths of past approaches and identifying gaps needed to make explanations user- and context-focused, we propose new definitions for explanations and explainable knowledge-enabled systems.
S. Chari, D. Gruen, O. Seneviratne, D. L. McGuinness, "Foundations of Explainable Knowledge-Enabled Systems". In: Ilaria Tiddi, Freddy Lecue, Pascal Hitzler (eds.), Knowledge Graphs for eXplainable AI -- Foundations, Applications and Challenges. Studies on the Semantic Web, IOS Press, Amsterdam, 2020, to appear
References in corpus (9)
- Towards A Rigorous Science of Interpretable Machine Learning
- Explaining Explanations in AI
- What do we need to build explainable AI systems for the medical domain?
- A systematic review and taxonomy of explanations in decision support and recommender systems
- One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
- AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
- Broadening the Scope of Nanopublications
- Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations
- Contrastive Explanations with Local Foil Trees
Cited by in corpus (4)
- Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes
- GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
- Brain-inspired Search Engine Assistant based on Knowledge Graph
- Benchmark datasets for biomedical knowledge graphs with negative statements