The time slot for a presentation is approximately 25 minutes.
Section: I. NLP Applications
chair: Aleš Horák
Adam Rambousek (presentation)
New Technology Platform for the Multilingual Sign Language Dictionary
Mikuláš Bankovič, Vít Novotný and Petr Sojka (presentation)
Application of Super-Resolution Models in Optical Character Recognition of Czech Medieval Texts
Ondřej Sotolář, Jaromír Plhák, Michal Tkaczyk, Michaela Lebedíková and David Šmahel (presentation)
Detecting Online Risks and Supportive Interaction in Instant Messenger Conversations using Czech Transformers
Vít Novotný, Kristýna Seidlová, Tereza Vrabcová and Aleš Horák (presentation)
When Tesseract Brings Friends: Layout Analysis, Language Identification, and Super-Resolution in the Optical Character Recognition of Medieval Texts
Ondřej Herman (presentation)
Precomputed Word Embeddings for 15+ Languages
Section: II. Semantics and Language Modelling
chair: Petr Sojka
Marek Menšík, Adam Albert and Tomáš Michalovský (presentation)
Using FCA and Concept Explications for Finding an Appropriate Concept
Marek Medveď, Radoslav Sabol and Aleš Horák (presentation)
Evaluating Long Contexts in the Czech Answer Selection Task
Marie Duží (presentation)
Questions and Answers on Dynamic Activities of Agents
Martina Číhalová (presentation)
Conceptual Framework for Process Ontology
Michal Štefánik and Petr Sojka (presentation)
Towards Domain Robustness of Neural Language Models
Section: III. Morphology and Syntax
chair: Pavel Rychlý
Vojtěch Mrkývka (presentation)
Approaching Punctuation Errors in the New Proofreader of Czech
Edoardo Signoroni (presentation)
Evaluating the State-of-the-Art Sentence Alignment System on Literary Texts
Helena Medková (presentation)
Building a Dataset for Detection of Verb Coordinations with a Shared Argument
Vojtěch Kovář and Pavel Rychlý (presentation)
DMoG: A Data-Based Morphological Guesser
Section: IV. Text Corpora
chair: Vojtěch Kovář
Michaela Denisová and Pavel Rychlý (presentation)
When Word Pairs Matter
Krištof Anetta and Mahmut Arslan (presentation)
Transferability of General Polish NER to Electronic Health Records
Maria Khokhlova (presentation)
A Case Study of High-Frequency Dictionary Collocations in a Spoken Corpus
Vít Suchomel and Jan Kraus (presentation)
Website Properties in Relation to the Quality of Text Extracted for Web Corpora
Miloš Jakubíček, Emma Romani, Pavel Rychlý and Ondřej Herman (presentation)
Development of HAMOD: a High Agreement Multi-lingual Outlier Detection dataset
Closing the Workshop