@incollection{DiewaldKupietzLuengen2022, author = {Nils Diewald and Marc Kupietz and Harald L{\"u}ngen}, title = {Tokenizing on scale. Preprocessing large text corpora on the lexical and sentence level}, series = {Dictionaries and Society. Proceedings of the XX EURALEX International Congress, 12-16 July 2022, Mannheim, Germany}, editor = {Annette Klosa-K{\"u}ckelhaus and Stefan Engelberg and Christine M{\"o}hrs and Petra Storjohann}, publisher = {IDS-Verlag}, address = {Mannheim}, isbn = {978-3-937241-87-6}, doi = {10.14618/ids-pub-11146}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-111464}, pages = {208 -- 221}, year = {2022}, abstract = {When comparing different tools in the field of natural language processing (NLP), the quality of their results usually has first priority. This is also true for tokenization. In the context of large and diverse corpora for linguistic research purposes, however, other criteria also play a role – not least sufficient speed to process the data in an acceptable amount of time. In this paper we evaluate several state of the art tokenization tools for German – including our own – with regard to theses criteria. We conclude that while not all tools are applicable in this setting, no compromises regarding quality need to be made.}, language = {en} }