Transparency & Explainability in AI

Semantic Web approach for linked model and data cards in AI systems

Transparency & Explainability in AI

Overview

This project explores transparency and explainability in AI systems using Semantic Web technologies.

Funding

  • Insight Research Ireland (Grant Number 12/RC/2289_P2)

Duration

Dec 2022 – Aug 2023

Team

  • PI: Dr Ihsan Ullah
  • Co-PIs: Edward Curry, Andy Donald

Researchers

Andy Donald; Apostolos Galanopoulos; Edward Curry; Emir Muñoz; Ihsan Ullah; M. A. Waskow; Manan Kalra; Sagar Saxena; Talha Iqbal

Description

The project transforms Model Cards, Data Cards, and Dataspace Cards into Linked Data representations.

  • Introduces a linking vocabulary for card ontologies
  • Enables integration with knowledge graphs
  • Demonstrates use cases:
    • Bias detection
    • Sentiment and emotion analysis

Thematic Areas

  • Artificial Intelligence / Machine Learning
  • Data Science
  • Knowledge Graphs & Linked Data

Impact

  • SDG 9: Industry, Innovation & Infrastructure