Linguistic Engineering Group
The Linguistic Engineering Group deals with multiple aspects of Natural Language Processing, such as information extraction, corpus linguistics and processing text at the semantic level.
View groupDepartment of Language Modeling
Institute of Computer Science, Polish Academy of Sciences
Research groups
Formal Linguistics Group
The Formal Linguistics Group (FLG) studies the syntactic and semantic structure of natural languages, employing corpus-based, computational, experimental and formal methods.
View groupCurrent events
SEMINAR • April 27, 2026
Seminar: Multidimensional Analysis (MDA) of the Polish Eurolect and National Varieties of Administrative Language
Łucja Biel, Katarzyna Wasilewska, and Dariusz Koźbiał (Institute of Applied Linguistics, University of Warsaw) will present a multidimensional analysis of the Polish Eurolect compared with the national variety of Polish administrative language.
Announcement • March 27, 2026
Report on the Use of AI in Digital Accessibility Research
Researchers from the Institute of Computer Science of the Polish Academy of Sciences and Sages prepared a report, commissioned by the Ministry of…
Event • September 20, 2025
PLLuM at Science with the Palace in the Background
The Institute of Computer Science of the Polish Academy of Sciences cordially invites you to its stand at the Palace in Jabłonna on September 20,…
Selected research projects
Ministry of Digital Affairs grant
PLLuM – Polish Large Language Model
The consortium’s goal is to develop the first open Polish LLM and an associated smart assistant. The project will adhere to ethical and responsible best practices in AI, incorporating data representativeness, transparency and fairness.
Lead: Maciej Ogrodniczuk
CLARIN ERIC
PressMint
PressMint is a CLARIN flagship project that aims to compile a multilingual, comparable, annotated, translated and interoperable set of corpora of European historical newspapers from around the start of the 20th century.
Lead: Maciej Ogrodniczuk
Polish National Science Centre grant
Universal Discourse: a multilingual model of discourse relations
The project intends to create a unified description of discourse relations (at the level of discourse markers, relation arguments and types) in the multilingual setting by harmonizing current corpus-based discourse representation models.
Lead: Maciej Ogrodniczuk