Belval, Luxembourg, 2017–2018

Information extraction Mémorial C

The project completed the digitization of Mémorial C, which – until 2016 – was the repertory all societies and companies in Luxembourg. The project’s purpose was to make the information contained in this government publication available for research by detecting the language and by extracting and identifying all entities (organisations, people, location, dates). To this end the project also developed a machine learning model on the domain vocabulary.

The project was commissioned by the Centre for Contemporary and Digital History (C²DH) at the University of Luxembourg.