Paul Groth, a professor of Algorithmic Data Science at the University of Amsterdam where he leads the Intelligent Data Engineering Lab (INDElab), will present "Knowledge (Graphs) in the Language Model Era."
Paul Groth is a Professor of Algorithmic Data Science at the University of Amsterdam where he leads the Intelligent Data Engineering Lab (INDElab). He holds a Ph.D. in Computer Science from the University of Southampton (2007) and has done research at the University of Southern California, the Vrije Universiteit Amsterdam and Elsevier Labs. His research focuses on intelligent systems for dealing with large amounts of diverse contextualized knowledge with a particular focus on web and science applications. This includes research in data provenance, data integration and knowledge sharing.
Large language models provide both an effective mechanism for extracting knowledge as well as a source of knowledge itself. This duality provides new opportunities for thinking about the architectures we use to obtain, curate, and expose knowledge. In this talk, I discuss our recent work on using language models for knowledge graph completion, and construction from text and video. I look discuss future thinking on new architectures can take advantage of the multiple representations of knowledge.
Gytė Tamašauskaitė and Paul Groth. 2023. Defining a Knowledge Graph Development Process Through a Systematic Review. ACM Trans. Softw. Eng. Methodol. 32, 1, Article 27 (January 2023), 40 pages. https://doi.org/10.1145/3522586
Melika Ayoughi, Pascal Mettes, and Paul Groth. 2023. Self-contained Entity Discovery from Captioned Videos. ACM Trans. Multimedia Comput. Commun. Appl. 19, 5s, Article 177 (October 2023), 21 pages. https://doi.org/10.1145/3583138
Daniel Daza, Michael Cochez, and Paul Groth. 2021. Inductive Entity Representations from Text via Link Prediction. In Proceedings of the Web Conference 2021 (WWW '21). Association for Computing Machinery, New York, NY, USA, 798–808. https://doi.org/10.1145/3442381.3450141
Knowledge-centric Prompt Composition for Knowledge Base Construction from Pre-trained Language Models (At the ISWC LM-AKBC workshop)
Do Instruction-tuned Large Language Models Help with Relation Extraction? (At the ISWC LM-AKBC workshop)
We continue the CIRSS speaker series in Fall 2023 with a focus on “Knowledge Graphs and Semantic Computing”. We will meet on Fridays, 9-10am Central Time, on Zoom. To join a session, go to the current week’s session and click the “access” link, which will lead you to a calendar entry. There, click the “PARTICIPATE online” button to join a session. Recordings of past talks can be found next to "access" if available. The event is open to the public, and everyone is welcome to attend! This series is hosted by the Center for Informatics Research in Science and Scholarship (CIRSS). If you have any questions, please contact Jana Diesner and Halil Kilicoglu.
This event is sponsored by Center for Informatics Research in Science and Scholarship