Digital Text Analysis Working Group: Dr. Jörg Wettlaufer and Sree Ganesh Thotempudi "Named Entity Recognition in Historical Corpora. Lessons learned so far… "

, 12:00 pm to


NER is a basic technology for knowledge extraction from texts. It is, however, far from being a standardized procedure for historical text corpora. We would like to present the results of our several-month endeavour to identify persons, places, technical terms, and dates in an 18th century manual of natural history by means of list- and rule-based approaches.

Presentation Slides