Mareček, David

1. Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages
   2023/05/26 by Tomasz Limisiewicz, Limisiewicz, Tomasz, Jiří Balhar +3 · 18 citations
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
2. Introducing Orthogonal Constraint in Structural Probes
   2020/12/30 by Limisiewicz, Tomasz, Mareček, David · 5 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences
3. Debiasing Algorithm through Model Adaptation
   2023/10/29 by Limisiewicz, Tomasz, Mareček, David, Musil, Tomáš · 5 citations
   #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (stat.ML)
4. From Balustrades to Pierre Vinken: Looking for Syntax in Transformer\n Self-Attentions
   2019/06/05 by David Mareček, Rudolf Rosa, Mareček, David +1 · 1 citation
   Engineering · Computer Science · #Ferroelectric and Negative Capacitance Devices #Parallel Computing and Optimization Techniques #Topic Modeling
5. Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
   2023/09/21 by Bar Iluz, Tomasz Limisiewicz, Iluz, Bar +5 · 2 citations
   Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Authorship Attribution and Profiling #Computation and Language (cs.CL) #FOS: Computer and information sciences #Gender Studies in Language #Natural Language Processing Techniques
6. Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information
   2022/06/21 by Limisiewicz, Tomasz, Mareček, David · 1 citation
   #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
7. Closing the loop: Autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments
   2023/06/20 by Linus Pithan, Pithan, Linus, Vladimir Starostin +23 · 1 citation
   Materials Science · #Machine Learning in Materials Science #Electron and X-Ray Spectroscopy Techniques
8. Inducing Syntactic Trees from BERT Representations
   2019/06/27 by Rudolf Rosa, David Mareček, Rosa, Rudolf +1 · 1 citation
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling