Conference Program

The time slot for a presentation is approximately 25 minutes.

Friday December 6, 2024

Section: I. Semantics and Language Modelling
chair: Aleš Horák

Petr Zelina (presentation)
From Examples to Patterns: LLM-Generated Regular Expressions for Entity Extraction in Czech Clinical Texts
Tereza Vrabcová and Petr Sojka (presentation)
Negation Disrupts Compositionality in Language Models: The Czech Usecase
Marek Medveď, Radoslav Sabol and Aleš Horák (presentation)
SlamaTrain - Representative Training Dataset for Slavonic Large Language Models

Section: II. Evaluation Methods
chair: Miloš Jakubíček

Michaela Denisová and Pavel Rychlý (presentation)
Fantastic Examples and Where to Find Them: Compiling Czech Dataset for Evaluating Dictionary Examples
Vojtěch Formánek and Ondřej Sotolář (presentation)
Quantitative Assessment of Intersectional Empathetic Bias and Understanding
Zuzana Nevěřilová and Hana Žižková (presentation)
Named Entity Alignment in Czech-English Parallel Data
Kristof Anetta (presentation)
Annotating Health Records: Does Ground Truth Even Exist?

Saturday December 7, 2024

Section: III. Text Corpora
chair: Pavel Rychlý

Matúš Kleštinec (presentation)
Impact of Data Split and Vocabulary Size in Neural Machine Translation for Slovak Language
Jakub Stetina, Martin Fajcik, Michal Štefánik and Michal Hradis (presentation)
A Comparative Study of Text Retrieval Models on DaReCzech
Vlasta Ohlídalová and Miloš Jakubíček (presentation)
A New Czech Pipeline in Sketch Engine
Maria Khokhlova and Natalia Safonova (presentation)
Rubric Extraction for Popular Science Articles in the Russian Language

Section: IV. NLP Applications
chair: Petr Sojka

Nataliia Časnochova Zozuk, Lívia Kelebercová and Daša Munková (presentation)
Lexical Density in Slovak Speech: A Non-invasive Indicator for Alzheimer’s Disease and Mild Cognitive Impairment
Emma Bednaříková and Pavel Rychlý (presentation)
Improvement of Language Identification Processing Speed
Michal Spiegel and Aleš Horák (presentation)
WebMap: Improving LLM Web Agents with Semantic Search for Relevant Web Pages
Hien Thi Ha (presentation)
Improving Layout Analysis of Scanned Invoices Using Line Detection

Sunday December 8, 2024

Closing the Workshop