Conference Program

The time slot for a presentation is approximately 25 minutes.

Friday December 5, 2025

Section: I. Evaluation Methods
chair: Aleš Horák

Michaela Denisová and Pavel Rychlý (presentation)
Lost in Morphology
Lucia Makaiová, Martin Fajčík and Antonín Jarolím (presentation)
Examining the Metrics for Document-Level Claim Extraction in Czech and Slovak
Antonín Jarolím, Martin Fajčík and Lucia Makaiová (presentation)
Can LLMs Extract Human-like Fine-grained Evidence for Evidence-based Fact-checking?
Matúš Kleštinec, Martin Chotár and Daša Munková (presentation)
Can Large Language Models substitute Human Annotators in Machine Translation Usability Assessment?
Emma Bednaříková and Pavel Rychlý (presentation)
Evaluating Training Data Construction Strategies for Token-Level Language Identification

Section: II. Semantics and Language Modelling
chair: Petr Sojka

Edoardo Signoroni and Pavel Rychlý (presentation)
Prompting Large Language Models for Church Slavic Translation
Marek Medveď, Radoslav Sabol, Ondřej Sotolář and Aleš Horák (presentation)
High-Quality LLM Pre-Training Texts from Dictionary Data
Radoslav Sabol and Aleš Horák (presentation)
Fine-grained and Dense Annotation of Czech Propaganda Using Large Language Models
David Porteš (presentation)
Prosody Interaction with Speech Planning and Comprehension, a Survey of Interesting Effects in the Literature

Saturday December 6, 2025

Section: III. Text Corpora
chair: Miloš Jakubíček

Patrik Stano (presentation)
Fast and Furious: Semantic Drift
Kristof Anetta and Aleš Horák (presentation)
Measuring Redundancy in Czech Electronic Health Records: Near-Duplicate Detection and Cluster Analysis
Jan Brichta (presentation)
Filtering of Czech Texts
Alena Němcová Polická and Pavel Rychlý (presentation)
Database and Corpora Creation within RapCor Project for Czech
Maria Khokhlova
Verbs of Motion in Russian: A Corpus Study of Quantitative Features

Section: IV. NLP Applications
chair: Pavel Rychlý

Dávid Držík and Lívia Kelebercová (video presentation)
Hate and Toxic Speech Detection in Slovak: Comparing BPE and Morphology-Based Tokenization Approaches
Marek Blahuš and Katarína Petreková (presentation)
Lemmatization of Czech and Croatian Noun Clusters for Terminology Extraction
Ondřej Metelka and Petr Sojka (presentation)
Hyph-bench: Benchmark Dataset of Hyphenated Words for Generating Hyphenation Patterns
Ondřej Herman (presentation)
Evaluating Trends in Czech and English

Sunday December 7, 2025

Closing the Workshop