Normalization of a Historic Western Ukrainian orthographic system Zhelekhivka in the Ukrainian Language Reference Corpus (GRAC)

The article describes the normalization of texts written using the Western Ukrainian orthographic system Zhelekhivka (1886-1940s). This stage is necessary for the qualitative lemmatization of such texts when adding them to a reference corpus of the Ukrainian language. The paper describes the main features of this orthographic system, suggests the rules of normalization, and discusses effectiveness of lemmatization based on these rules.