|Title||Wikipedia Knowledge Graph for Explainable AI|
|Publication Type||Conference Papers|
|Year of Publication||2020|
|Authors||Sarker, MK, Schwartz, J, Hitzler, P, Zhou, L, Nadella, S, Minnery, B, Juvina, I, Raymer, ML, Aue, WR|
|Conference Name||Second Iberoamerican Knowledge Graphs and Semantic Web Conference (KGSWC)|
Explainable artificial intelligence (XAI) requires domain information to explain a system's decisions, for which structured forms of domain information like Knowledge Graphs (KGs) or ontologies are best suited. As such, readily available KGs are important to accelerate progress in XAI. To facilitate the advancement of XAI, we present the Wikipedia Knowledge Graph (WKG), based on information from English Wikipedia. Each Wikipedia article title, its corresponding category, and the category hierarchy are transformed into different entities in the knowledge graph. As the Wikipedia category hierarchy is not a tree, instead forming a graph, to make the finding process of the parent category easier, we break cycles in the category hierarchy. We evaluate whether the WKG is helpful to improve XAI compared with existing KGs, finding that WKG is better suited than the current state of the art. We also compare the cycle-free WKG with the Suggested Upper Merged Ontology (SUMO) and DBpedia schema KGs, finding minimal to no information loss.