Computational Linguistics

Every year, philology students who elect courses in computational linguistics become involved in the development of the following projects:

  • Large Electronic Dictionary of Ukrainian (VESUM, around 400,000 lemmas, over 6 million wordforms)
  • General Regionally Annotated Corpus of Ukrainian (GRAC, over 500 million tokens)
  • Spelling, grammar and style checker Pravopysnyk LanguageTool for Ukrainian
  • Ukrainian Brown Corpus (BrUC)

A number of successfully defended course papers and bachelor’s theses have contributed to the development of these and other projects, including the creation of a therapist chatbot and automatic placement on the political compass based on an analysis of a person’s tweets.