Dr. rer. nat., Dipl.-Phys., Dipl.-Wirtsch. Phys.
I am a Digital Humanist, using computational tools and methods to investigate disciplinary research questions in the humanities.
Specifically, I am trying to make our cultural heritage data embodied in early printed books (starting from the invention of modern printing by Gutenberg ca. 1450) available for analysis as machine-actionable research data. This involves advanced OCR (optical character recognition) methods based upon recurrent neural networks to convert digitized page images to electronic text, statistical postcorrection tools for historical spellings, and properly marked-up data and metadata to enable automatic and semi-automatic analysis.
These activities also entail a fair amount of Latin, the predominant literary language in the early modern period of western culture.
I am currently affiliated with:
Previously I worked at:
Center für Informations- und Sprachverarbeitung (CIS) at Ludwig-Maximilians-Universität München;
Institut für deutsche Sprache und Linguistik at Humboldt-Universität zu Berlin;
✉ firstname (at) lastname (dot) net