Talks | Lukas Paul Achatius Galke

Talks

Invited talks

  • [t37] Lukas Galke (2024, July 4). Machine Communication and the Emergence of Language. MPI Proudly Presents, Nijmegen.
  • [t36] Lukas Galke (2024, June 19). Machine Communication. IMADA Seminar, SDU Odense.
  • [t35] Lukas Galke (2024, June 10). Emergent communication and learning pressures in language models [invited talk]. ANN Humlang workshop, Amsterdam.
  • [t33] Lukas Galke (2024, May 3). Learning Pressures and Inductive Biases in Neural Language Models [invited talk]. Meeting of Creative Intelligence Lab, Leiden, Netherlands.
  • [t29] Lukas Galke (2023, July 20). What makes a language easy to deep-learn? [invited talk]. Colloquium Cognitive Systems, University of Ulm, Germany.
  • [t28] Lukas Galke (2023, July 10). Lifelong Learning and Out-of-distribution Detection on Evolving Graphs [invited talk], VU AI Colloquium, Amsterdam, The Netherlands.
  • [t27] Lukas Galke (2023, July 5). Lifelong Neural Communication [informal invited talk]. Data Science, Hamburg University, Germany.
  • [t26] Lukas Galke (2023, May 17). Uncovering Patterns in Medical Literature through Lifelong Automated Categorization and Research Dynamics Analysis with Machine Learning [informal invited talk]. KIK AI Coffee & Learning meeting, Amsterdam University Medical Centre, The Netherlands.
  • [t25] Lukas Galke (2023, May 16). What makes a language easy to deep-learn? [invited talk]. Computational Linguistics Seminar, University of Amsterdam, The Netherlands.
  • [t24] Lukas Galke (2023, February 27). What makes a language easy to deep learn? [invited talk]. Language Evolution and Emergence meeting, Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands.
  • [t23] Lukas Galke (2022, October 20). Structure in Language Learning Systems [informal invited talk]. TALEP Marseille, France.

Conference and workshop presentations

  • [t38] Lukas Galke (2024, July 9). Harnessing Cross-lingual Morphological Generalization Abilities in Large Language Models with a Multilingual Wug Test [poster]. Highlights in the Language Sciences Conference, Nijmegen.
  • [t34] Lukas Galke (2024, May 20). Learning Pressures and Inductive Biases in Emergent Communication: Parallels between Humans and Deep Neural Networks. Evolang XV, May 20, 2024.
  • [t30] Lukas Galke (2023, September 28). What makes a language easy to deep-learn? Protolang 8, Rome, Italy.
  • [t22] Lukas Galke (2022, September 5). Machine Learning for Language Evolution – What’s missing?. Machine Learning and the Evolution of Language (ml4evolang) workshop at JCOLE’22, Japan/online.
  • [t19] Lukas Galke (2022, July 19). General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings [paper presentation (oral)]. World Congress on Computational Intelligence, Padua, Italy.
  • [t18] Lukas Galke (2022, June 1). Emergent Communication for Understanding Human Language Evolution: What’s missing? [paper presentation (poster)]. IMPRS conference, Nijmegen, The Netherlands.
  • [t17] Lukas Galke (2022, May 24). Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP [paper presentation (oral)]. ACL 2022. video
  • [t16] Lukas Galke (2022, April 29). Emergent Communication for Understanding Human Language Evolution [paper presentation (oral) and discussion session]. EmeCom workshop at ICLR’22, online.
  • [t15] Lukas Galke (2021, December 15). COVID-19++: A Citation-Aware Covid-19 Dataset for the Analysis of Research Dynamics [paper presentation (oral)]. 2021 IEEE International Conference on Big Data (Big Data), online.
  • [t14] Lukas Galke (2021, July 18). Lifelong learning of graph neural networks for open-world node classification [paper presentation (oral)]. International Joint Conference on Neural Networks, online.
  • [t12] Lukas Galke (2019, September 26). Inductive Learning of Concept Representations from Library-Scale Corpora with Graph Convolution [paper presentation (oral)], INFORMATIK 2019, Kassel, Germany.
  • [t11] Lukas Galke (2019, September 26). What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function [paper presentation (oral)]. INFORMATIK 2019, Kassel, Germany
  • [t10] Lukas Galke, Florian Mai (2019, May 8). CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model [paper presentation (poster)]. International Conference on Learning Representations, New Orleans, Lousiana.
  • [t9] Lukas Galke (2019, May 7). Can Graph Neural Networks Go Online? An Analysis of Pretraining and Inference [paper presentation (poster)]. International Conference on Learning Representations, New Orleans, Lousiana.
  • [t8] Anne Lauscher, Lukas Galke, Syed Tahseen Raza Rizvi (2018, November 6). LOC-DB Evaluation: criteria and preliminary results. Second Linked Open Citation Database (LOC-DB) workshop. [project presentation]
  • [t7] Lukas Galke (2018, July 10). Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels [paper presentation (oral)]. Conference on User Modeling, Adaptation and Personalization, Singapore, Singapore.
  • [t6] Lukas Galke (2017, December 6). Using Titles vs. Full-text as Source for Automated Semantic Document Annotation [paper presentation (oral)], Knowledge Capture Conference, Austin, Texas.
  • [t5] Kai Eckert, Anne Lauscher, Lukas Galke (2017, November 7). LOC-DB Konzepte. First Linked Open Citation Database (LOC-DB) Workshop. [project presentation]
  • [t4] Lukas Galke (2017, September 28). Reranking-based Recommender Systems with Deep Learning [paper presentation (oral)]. INFORMATIK 2017, Chemnitz, Germany.
  • [t3] Lukas Galke (2017, September 28). Word Embeddings for Practical Information Retrieval [paper presentation (oral)]. INFORMATIK 2017, Chemnitz, Germany.
  • [t2] Lukas Galke (2017, May 5). Embedded Retrieval: Word Embeddings for Practical Information Retrieval [M.Sc. thesis presentation]. Second DyESE workshop, Kiel, Germany.
  • [t1] Lukas Galke (2016, September 16). Information Retrieval on Sparse Data [concept presentation]. First DyESE workshop, Oslo, Norway.

Other

  • [t21] Lukas Galke (2022, August 28). Representation Learning for Texts and Graphs [viva]. Department of Computer Science, Kiel University, Germany.
  • [t20] Lukas Galke (2022, August 18). Language Technology [gave a 2x45min workshop to a broad audience]. Regiodag 2022 Probusclub Nijmegen e.o., Nijmegen, The Netherlands.
  • [t13] Lukas Galke (2020, June 23). Scaling Up Graph Neural Networks [literature review talk], Graph Neural Networks Reading Group, online.

Contact: lukas 'at' lpag.de
Design: Adapted from Diane Mounter.
Privacy: No personal data, no cookies.