I am a rising statistician and a data scientist in the final year of MSc Methodology and Statistics at Utrecht University. My primary project is the development of a new feature attribution technique for transformer language models such as BERT which can be used to explain which words, phrases and sentences are driving their predictions. I am always curious and in awe about something. This is reflected in my side projects which I greatly enjoy:
- Collaboration on an article about best practices in latent class analysis using free open source software
- Collaboration on a systematic review about the use of active learning for systematic reviews
- Collaboration on the implementation of state-of-the-art feature selection methods for the R package
mice
(Multivariate Imputation by Chained Equations)
Interests:
- NLP & Text-Mining
- Algorithmic Fairness & Explainable AI (XAI)
- Feature Attribution & Feature Selection
- Active Learning & Deep Learning
- Systematic Reviews
- Latent Class Analysis & Structural Equation Modeling
Active in:
Consultation:
I find problem-solving and knowledge-sharing incredibly fulfilling! If you think I might be able to help, don’t hesitate to reach out!