- From: Olaf Hartig <olaf.hartig@liu.se>
- Date: Tue, 9 Jan 2024 20:45:30 +0000
- To: "semantic-web@w3.org" <semantic-web@w3.org>
Dear all, I am happy to announce the next talk in the online talk series [1] of the COST Action on Distributed Knowledge Graphs (DKG) [2], in collaboration with the Semantic Web Science Association (SWSA) [3]. On January 17 at 18:00 CET / 12:00 EST, Ilaria Tiddi (Vrije Universiteit Amsterdam) will talk about: Explainability with Knowledge Graphs: what have we learnt? Abstract: We hear about explanations for AI all the time these days, since the the latest (deep) machine learning solutions revealed to provide highly accurate, but hardly scrutable and interpretable decisions. In 2013, we were looking into using Knowledge Graphs to create explanations from ML outputs, well before we even heard of the term eXplainable AI (XAI, coined by DARPA in 2017). In this teasing talk, we will look into this work from today’s perspective, including what has been done in this context, whether it is still useful and relevant, and whether the same methods still apply. We will conclude with a discussion on the future of these ideas, hoping to foster new research in this direction. Speaker: Ilaria Tiddi is an Assistant Professor in Hybrid Intelligence at the Knowledge in AI (KAI) group of the Vrije Universiteit Amsterdam (NL). Her research focuses on creating systems that generate complex narratives through a combination of semantic technologies, open data and machine learning, applied mostly in scientific and robotics scenarios. She is Editor-in-Chief of the CEUR-WS publication, part of the Steering Committee for the Hybrid Human-AI Conference, and Coordinator of the international Staff Exchange for the Dutch Hybrid Intelligence consortium. Since 2014, she is regularly active in the OCs/PCs of the major venues in the KR field (ISWC/ESWC, HHAI, WWW, CIKM, IJCAI/ECAI). The talk will be live streamed at our YouTube channel: https://www.youtube.com/@costdkg4356/streams In addition to Ilaria's talk, mark your calendars already for the following upcoming talks in the talk series. * Mayank Kejriwal (University of Southern California) "Neurosymbolic Approaches for Robust Domain-Specific Semantic Search: Current Progress and Future Opportunities" January 31 at 18:00 CET / 12:00 EST * Mark A. Musen (Stanford University) "Semantic Technology in Science: Enhancing Data Stewardship in Support of New Discovery" March 4 at 18:00 CET / 12:00 EST * Peter F. Patel-Schneider "Does the Knowledge Graphs Community care about semantics?" April 17 at 18:00 CET / 12:00 EST Best regards, Olaf [1] https://cost-dkg.eu/talks [2] https://cost-dkg.eu/ [3] https://swsa.semanticweb.org/
Received on Tuesday, 9 January 2024 20:45:41 UTC