How computational linguists are researching the Ukrainian language at GRAK 📚💻

Studying a language in the 21st century isn’t about looking up the meanings of words in paper tomes. It’s about working with millions of texts through specialised language corpora!

In practical classes on applied and computational linguistics, our students make active use of GRAK (the General Regionally Annotated Corpus of the Ukrainian Language):

How has the usage of certain words changed over the last century?

Identifying fixed word combinations (collocations) for machine translation.

Creating annotated text corpora for training Ukrainian-language NLP models.

This practical experience enables students not only to write coursework and research papers based on real-world data, but also to acquire the data annotation skills required by the IT sector.

Share to: