Lukas Galke
I’m Lukas, a postdoctoral researcher at the Max Planck Institute for Psycholinguistics. I’m most passionate about natural language processing and lifelong machine learning, while often engaging in interdisciplinary projects. Currently, I’m focusing on how deep neural networks learn to communicate and the parallels to human communication.
- learn more about my projects
- some non-professional things about me
- feel free to use this bio and picture if needed
Selected publications
- [j7] Lukas Galke, Yoav Ram, Limor Raviv (in revision). What makes a language easy to deep-learn?
- [j3] Lukas Galke, Iacopo Vagliano, Benedikt Franke, Tobias Zielke, Marcel Hoffmann, Ansgar Scherp (2023). Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes. Neural Networks 164, 156-176.
- [c9] Lukas Galke, Ansgar Scherp (2022). Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4038–4051, Dublin, Ireland. Association for Computational Linguistics.
Recent news
- Dec 2023: received best paper award from GenBench workshop, EMNLP 2023
- Jul 2023: received outstanding reviewer award from ACL 2023
- Jul 2023: gave a talk in the Cognitive Systems Colloquium, University of Ulm [t29]
- Jul 2023: gave a talk in the AI Colloquium of Vrije Universiteit Amsterdam [t28]
- May 2023: paper on lifelong graph learning published in Neural Networks [j3]
- May 2023: gave a talk in the KIK AI Coffee and Learning meeting at Amsterdam University Medical Centre [t26]
- May 2023: gave a talk in the Computational Linguistics Seminar at University of Amsterdam [t25]
Links
Contact
To get in touch, just drop me an e-mail via hi@lpag.de.