The topic of the research regards automated information extraction from unstructured and semi-structured documents and developing novel machine learning models that are self-learning and can be applied for real-time processing. Special attention will go to deep learning models relying on character-based or word-based representations of content.
The ideal candidate has a PhD or master degree in computer science or equivalent degree, has excellent study results, good knowledge of English, French and Dutch, and has a motivated interest in machine learning and text mining. In case of a master degree, we expect demonstrable experience in machine learning.
We offer a research position for one year (can be prolonged) in a team that has an outstanding international reputation for its language processing and text mining research.