Knowledge Graphs for AI: Wikidata and Beyond

Talk by Markus Krötzsch

Location: Online
Start: 11. February 2021 at 1:00 pm
End: 11. February 2021 at 2:30 pm
Event series: Research Seminar Logic and AI
iCal

Abstract:

"Wikidata, the knowledge graph of Wikimedia, has successfully grown from an experimental “data wiki” to a well-organized reference knowledge base with a large and active editor community as well as many academic and industrial uses. It is also a key ingredient of popular AI applications, most prominently of intelligent agents such as Apple's Siri or Amazon's Alexa. Of course, human knowledge is fully expected to be in high demand in this time of rapidly advancing AI. And yet, the fact that modern AI relies on the manual labor of thousands of human knowledge modelers is in stark contrast to the common narrative of AI in popular media, which tells us that methods of pattern recognition and statistical function approximation can produce intelligent behavior from unstructured data without much human intervention. However, Wikidata is not a singular exception to the trend but rather a specific solution to a general need of AI: the need for knowledge that is understandable to humans and accessible to computers. Almost every major AI application incorporates such knowledge, and organizations long have realized the need to acquire and develop knowledge resources as part of their AI strategy. The next frontier in AI is the ability of systems to explain and justify their behavior. There, too, we can see the need for knowledge-based technologies as a bridge between human understanding and computational mechanisms, but the task goes far beyond the realms of knowledge representation or machine learning, and will require the effort of all of AI and maybe all of computer science.

In my talk, I will give an overview of Wikidata and other knowledge-based technologies in AI, and outline some ongoing research efforts that combine knowledge representation with other methods towards the creation of (more) understandable and accountable AI."

This talk will have a duration of approximately 45 minutes and takes place via BigBlueButton. To access the room, use one of the following links:

with ZIH-Login:

https://selfservice.zih.tu-dresden.de/l/link.php?m=82158&p=3d86e9c8

without ZIH-Login:

https://selfservice.zih.tu-dresden.de/link.php?m=82158&p=506714c8