Lemmatization of the DIA1900 Diachronic Corpus

Abstract This paper focuses on the process of lemmatization of the upcoming Czech diachronic corpus of the second half of the 19 th century, DIA1900. The article describes different approaches to the corpus lemmatization of synchronic written, spoken and diachronic corpora within the Czech National Corpus project, including single- and multilevel lemmatization and available tools used to link the variants.