Welcome to our May meetup hosted by the Infosys Innovation Lab, Berlin. Doors open at 18:45.
Our main speaker will be Clemens Neudecker from the Berlin State Library:
Title: How to read a million books
Abstract: Thanks to digitization, today more than 55 million objects from the collections of Europe's libraries, archives and museums are available online to explore and reuse via Europe's digital library, Europeana. This talk will introduce some of the main activities, datasets and tools in the digitization of cultural heritage. The main focus will be on the Europeana Newspapers collection, a public domain licensed dataset of roughly 12 million pages of historic newspapers, and the possibilities and challenges in analyzing such large and heterogeneous textual resources with common NLP and machine learning tools.
Short Bio: Clemens Neudecker works as Research Coordinator at the Berlin State Library. He holds a Master of Arts in Philosophy, Computer Science and Political Science from the University of Munich (LMU). Since 2003, he has been implementing numerous international research and innovation projects in the field of digitisation of cultural heritage. He is a member of the ALTO Board and the founder of the KB Research Lab. Previously he was employed as Researcher in the Bavarian State Library and as Technical Coordinator Research in the National Library of the Netherlands. His personal interests lie in pattern recognition, text analysis and the digital humanities.
We have room for lightening talks. If you wish to give one, please email us at [masked] or approach us at the event.
Looking forward to seeing you there! And, as always, please remember to update your RSVP to ensure others have a chance to join.