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.

find more publications here

Links

• ORC ID: 0000-0001-6124-1092
• DBLP profile
• Semantic Scholar profile
• Google Scholar profile
• Github profile
• Mastodon account

Contact

To get in touch, just drop me an e-mail via hi@lpag.de.