Being one of several publishers of the German Yellow Pages, we have the need to categorise new, very large datasets. We discuss our process from a rule-based system using a knowledge graph towards a machine-learning approach as well as benefits of a mixed approach.
With the help of real-world data we explain how each of these approaches work.
Müller Medien GmbH & Co. KG
http://www.mueller-medien.com
Cora Scholl, born in 1992, has a Bachelor’s degree in information science (Hochschule Darmstadt, University of Applied Science). Her studies were strongly focused on knowledge representation and information architecture. Further, she began to study information science and speech technology (Heinrich Heine University, Düsseldorf).
Web analytics and taxonomy consulting
Müller Medien GmbH & Co. KG
http://www.mueller-medien.com
Rüdiger Schütz, studied German Languages (Linguistics) at the University of Duisburg/Essen. After finishing his university education first he worked at the publisher Data Becker, Düsseldorf, where he was responsible for leading the department of product management for language teaching software. Since 1996 he is leading a dept.
