Sara Veldhoen, Research Software Engineer. I hold a BSc degree in Artificial Intelligence from Utrecht University (UU) and an MSc degree in the same field from the University of Amsterdam (UvA), where I specialized in Natural Language Processing at the Institute for Logic, Language and Computation (ILLC).
I explore how computational methods (machine learning and more specifically: deep learning with neural networks) can be applied to textual data, that is by nature quite fuzzy and unstructured. I believe that formal linguistic structures can guide us to representations that are rich and flexible enough to capture the essence of natural language.
My focus at KB is on extracting metadata, such as topics/ keywords, from the items in the collection. Furthermore, I work together with humanities researchers in residence to extend their research in the digital and computational domain.