Wikipedia knowledge graph for explainable AI

Authors

Md Kamruzzaman Sarker, Kansas State University
Joshua Schwartz, Kansas State University
Pascal Hitzler, Kansas State University
Lu Zhou, Kansas State University
Srikanth Nadella, Kairos Research
Brandon Minnery, Kairos Research
Ion Juvina, Wright State University - Main CampusFollow
Michael L. Raymer, Raymer
William R. Aue, Wright State University

Document Type

Article

Publication Date

1-1-2020

Identifier/URL

40277143 (Pure); 85098259489 (QABO)

Find this in a Library

Catalog Record

Abstract

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 cycle-free 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. Along with cycle-free version we also provide the original knowledge graph as it is. 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.

Comments

Publisher Copyright: © Springer Nature Switzerland AG 2020.

Repository Citation

Sarker, M. K., Schwartz, J., Hitzler, P., Zhou, L., Nadella, S., Minnery, B., Juvina, I., Raymer, M. L., & Aue, W. R. (2020). Wikipedia knowledge graph for explainable AI. Knowledge Graphs and Semantic Web - Second Iberoamerican Conference and First Indo-American Conference, KGSWC 2020, Proceedings, 72-87.
https://corescholar.libraries.wright.edu/psychology/650

DOI

10.1007/978-3-030-65384-2_6