Institute of Computer Science, Polish Academy of Sciences

Department of Language Modelling

The Department of Language Modelling pursues research on natural language at the intersection of linguistics and computer science. Through its two complementary research groups it combines applied Natural Language Processing — information extraction, semantic text processing, and corpus linguistics — with formal investigation of syntactic and semantic structure, producing many of the resources, tools, and theoretical results that underpin language technology for Polish. Choose a group below to explore its faculty, publications, and ongoing projects.

Head of the Department

Research Groups

Research Group

Linguistic Engineering Group

Works on Natural Language Processing with a focus on information extraction, semantic text processing, and corpus linguistics. The team develops widely used resources and open-source tools for Polish — including the National Corpus of Polish (NKJP), the Polish Dependency Treebank, the Grammatical Dictionary, TermoPL/TermoUD, LAMBO, COMBO, Morfeusz, and Korpusomat — and participates in CLARIN-PL, DARIAH-PL, and COST initiatives.

Members

Research Group

Formal Linguistics Group

Studies the syntactic and semantic structure of natural languages using corpus-based, computational, experimental, and formal methods. Members have contributed to key Polish resources such as NKJP, the Walenty valence dictionary, and the UD-LFG corpus, and pursue theoretical work on coordination, quantification, argument structure, and the multifunctional Polish word to, in collaboration with researchers at Oxford, Konstanz, and MIT.

Members