Department of Language Modeling

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nulla aliquam arcu neque, eget ornare arcu vehicula in. Pellentesque ac dignissim nunc. Praesent vulputate turpis ac consectetur pellentesque. Ut ac dolor nec lacus mattis tincidunt. In hac habitasse platea dictumst. Aenean justo justo, fermentum at turpis et, dignissim tristique nulla. Duis ullamcorper erat ligula, ac tempus dui pharetra scelerisque. Aliquam erat volutpat. Cras ultrices sit amet ipsum sed maximus. Praesent mollis risus a ornare ultricies. Fusce eget urna odio. Nullam venenatis sapien sed tincidunt semper.

In turpis arcu, elementum at accumsan eu, pulvinar et ante. Suspendisse potenti. Sed eu lorem nec leo placerat efficitur. Aenean purus sapien, lacinia at sollicitudin ac, bibendum a tellus. Nam placerat lorem id accumsan dapibus. Proin malesuada augue id urna suscipit pulvinar. Aliquam erat volutpat. Fusce interdum accumsan interdum. Curabitur et odio luctus, iaculis tortor in, imperdiet urna. Nulla malesuada odio eu mi mattis, non pulvinar tellus egestas. Etiam erat metus, iaculis ac aliquet quis, venenatis vel dolor.

Publications by Maciej Ogrodniczuk

Selected works authored or co-authored by Maciej Ogrodniczuk from our institute bibliography.

2026

AI-Powered Knowledge Discovery in the Digital Library of Old Ephemeral Prints: A Case Study

Intelligence and Equity: Shaping the Future of Knowledge

Authors

Maciej Ogrodniczuk
Dariusz Czerski

Where Frameworks (Dis)agree: A Study of Discourse Segmentation

PLLuM: A Family of Polish Large Language Models

The PLLuM Instruction Corpus

Polish Round Table Corpus

Adopting ISO 24617-8 for Discourse Relations Annotation in Polish: Challenges and Future Directions

Curated Multilingual Language Resources for CEF AT (CURLICAT): Overall View

Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources

ParlaMint II: The Show Must Go On

Error Correction Environment for the Polish Parliamentary Corpus

ParlaMint: Comparable Corpora of European Parliamentary Data

New Developments in the Polish Parliamentary Corpus

The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe

The MARCELL Legislative Corpus

Automatyczne wykrywanie nominalnych zależności referencyjnych w polskich tekstach współczesnych

Polish Parliamentary Corpus

Analysis of Coreferential Expressions in PAWS (English-Czech-Russian-Polish Parallel Treebank with Anaphoric Relations)

Verbal Synaesthesia in the Polish Corpus of Synaesthetic Metaphors

Lingwistyka komputerowa dla języka polskiego: dziś i jutro

Metaphor Annotation in the Corpus of Polish

Šárka Zikánová – Eva Hajičová – Barbora Hladká – Pavlína Jínová – Jiří Mírovský – Anna Nedoluzhko – Lucie Poláková – Kateřina Rysová – Magdaléna Rysová – Jan Václ: Discourse and Coherence: From the Sentence Structure to Textual Relations

Narodowy Korpus Języka Polskiego – co dalej?

Web services and data mining: combining linguistic tools for Polish with an analytical platform

W poszukiwaniu metody automatycznego mierzenia zrozumiałości tekstów informacyjnych

Inter-annotator Agreement in Coreference Annotation of Polish

The same or just much the same? Problems with coreference from the reader's perspective

A Multi-purpose Online Toolset for NLP Applications

Interesting Linguistic Features in Coreference Annotation of an Inflectional Language

Discovery of Common Nominal Facts for Coreference Resolution: Proof of concept

Elektroniczny korpus tekstów polskich z XVII i XVIII w. (do 1772 r.) — prezentacja projektu badawczego

Cyfrowi mówcy uczą się szybko

Central and South-European language resources in META-SHARE

i-Librarian — Free online library for European citizens

Polish Language Processing Chains for Multilingual Information Systems

Semantic Approach to Identity in Coreference Resolution Task

i-Publisher, i-Librarian and EUDocLib – linguistic services for the Web

Merging heterogeneous resources and tools in a digital library

Digital Library of Poland-related Old Ephemeral Prints: Preserving Multilingual Cultural Heritage

Rule-based coreference resolution module for Polish

ATLAS — A Robust Multilingual Platform for the Web

UIMA-based processing of Polish

Multipurpose Linguistic Web Service for Polish

The Packaged TEI P5-based Stand-off Annotation Format

Integration of Language Resources into Web service infrastructure

ATLAS — The Multilingual Language Processing Platform

Cyfrowa Biblioteka Druków Ulotnych Polskich i Polski dotyczących z XVI, XVII i XVIII w. w nauce i dydaktyce

Linguistic processing chains as Web Services: Initial linguistic considerations

Weryfikacja korpusu wypowiedników polskich (z wykorzystaniem gramatyki formalnej Świdzińskiego)

An extension of Świdziński's grammar of Polish

Restructuring Świdziński's grammar of Polish

From SGML to XML with TEI: Automated conversion of a corpus of Polish from P3 to P4 format

Rozszerzenie opisów morfologicznych w tekstach korpusu „Słownika frekwencyjnego polszczyzny współczesnej”

Nowa edycja wzbogaconego korpusu słownika frekwencyjnego

Wzbogacenie korpusu słownika frekwencyjnego o nowe kody gramatyczne

Nowa edycja wzbogaconego korpusu słownika frekwencyjnego

Prace nad korpusem „Słownika frekwencyjnego języka polskiego”

Wykorzystanie SGML i TEI do zapisu polskich danych lingwistycznych