Abstract
In the project “Text+Berg” we digitize all yearbooks of the Swiss Alpine Club from 1864 until today. The books comprise articles in German, French and Italian, a total of around 100,000 pages. This paper describes the corpus and the project phases towards its digitalization. We then focus on the classification of named entities, in particular geographic entities. We explore the usefulness of a large list of geographical names that is distributed by the Swiss Federal Office of Topography. A first experiment indicates that the recognition and classification of geographical names remains difficult despite the large gazetteer.
Volk, Martin