Hands-on Automatic Quality Assessment of Knowledge Graphs

In this tutorial we will tackle the challenge of detecting and uncovering (potentially systematic) quality issues in knowledge graphs, in an as much as possible automatic way. We will cover quality dimensions like accuracy, completeness, conciseness and understandability, and we will apply problem detection methods inspired from linguistics, statistical modeling, and ontological analysis, in publicly available knowledge graphs.

By the end of this tutorial, the attendees will be able to:

Identify key quality dimensions that are important to measure in a knowledge graph, along with the typical reasons why a knowledge graph might have low scores in each of them.
Develop computational methods for automatically detecting and uncovering quality issues in each of these dimensions.

Delivery methodology and tentative schedule:

The tutorial is suggested to be delivered in 4 sessions of a total duration of 120 minutes, with one break in between. Each session will comprise a slide-based presentation of key topics and techniques, a hands-on demonstration of these techniques with relevant software, and a Q&A.