, Piotr Nowak
, Piotr Wierzchoń
https://doi.org/10.21697/kmt.2023.57.04
The aim of the article is to present a complex of methods aimed at compiling the Lexicon of Censorship. In particular, the authors’ intention is to discuss the problems which have been encountered in developing a list of entries for the planned publication and to indicate what novelty it will introduce to research on censorship. The authors discuss the previous works on censorship and describe the procedures for creating the lexicon with the use of digitized text resources contained in Polish digital libraries and other digital databases of texts (press, journalistic, artistic, etc.). The methods used were discussed, taking into account the use of information
contained in the literature on the subject and artificial intelligence techniques (including photodocumentation, word vectorization or transformer architecture). In addition, the authors present exemplary results of their work.
Język Polski
English