CLASSLA-Express Workshops in 2025

CLASSLA-Express: Workshops on using CLARIN.SI corpora, resources and AI tools in language research

By Dr. Nikola Ljubešić

CLASSLA-Express workshops aim to show participants how to use the CLASSLA web corpora in language research. The workshops comprise hands-on exercises showing how to create queries in corpora for Bulgarian, Croatian, Macedonian, Serbian and Slovene.

The workshops are based on using the CLARIN.SI NoSketch Engine concordancer in order to obtain data on meanings and uses of words, word forms, collocations and grammatical patterns. Moreover, the exercises will enable participants to explore uses of words and lexico-grammatical constructions in different types of texts. The focus will also be on testing how large language models (LLMs) perform linguistic tasks, identifying which tasks can be entrusted to them, and determining the tasks for which the traditional corpus-based research methods and concordancers are more suitable.

The workshops will focus on two key objectives: first, sharing knowledge on the usage of language tools; and second, to contribute to the development of a methodological framework for integrating AI tools into linguistic research. This framework will combine AI tools with corpus-based methods and establish criteria for evaluating their results. In doing so, we will further explore the benefits and challenges of incorporating LLMs into corpus linguistic research, aiming to create a methodologically sound approach for combining these two powerful toolsets.

The workshops are aimed at university students of South Slavic languages, linguists, lexicographers, language teachers and digital humanities scholars. They provide an opportunity for both beginners and more advanced corpus users to query corpora which reflect contemporary language use. Furthermore, the workshops will introduce users and researchers of Macedonian to the first general corpus of that language – CLASSLA-web.mk. The practical skills which participants will acquire may be applied in language teaching (both L1 and L2), designing corpus-informed dictionaries and grammars, as well as in digital humanities.