Simon Šuster


I'm a postdoc at the Computational Linguistics & Psycholinguistics Research Center (CLiPS) of the University of Antwerp, headed by Walter Daelemans. I completed my PhD at the University of Groningen, advised by Gertjan van Noord, and have worked closely with Ivan Titov. Prior to that, I was a master student in the LCT program and obtained my university degree in translation studies in Slovenia.

My broad research interests include natural language understanding and deep learning. I’m currently most enthusiastic about reading comprehension and question answering with neural models, and understanding what goes on under the hood of machine readers, especially when applied to specialized domains like medicine and healthcare. I have also worked in various domains of NLP, most prominently in information extraction, representation learning for words with linguistic biases, and ethics for NLP.

I co-advise two PhD students: Madhumita Sushil on interpretability and document representation learning, and Pieter Fivez on lexical normalization and modeling of lexical variability.

Publications

Talks

Teaching