raslan Ales Horák Pavel Rychlý Adam Rambousek The 18th Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2024 Tribun EU 2024 978-80-263-1835-4 RASLAN 18 Kouty nad Desnou, Czech Republic December 6-8, 2024 http://raslan2024.nlp-consulting.net/
I. Semantics and Language Modelling
Petr Zelina From Examples to Patterns: LLM-Generated Regular Expressions for Entity Extraction in Czech Clinical Texts 3-16 http://nlp.fi.muni.cz/raslan/2024/paper6.pdf Tereza Vrabcová Petr Sojka Negation Disrupts Compositionality in Language Models: The Czech Usecase 17-24 http://nlp.fi.muni.cz/raslan/2024/paper11.pdf Marek Medved Radoslav Sabol Ales Horák SlamaTrain - Representative Training Dataset for Slavonic Large Language Models 25-33 http://nlp.fi.muni.cz/raslan/2024/paper13.pdf
II. Evaluation Methods
Michaela Denisová Pavel Rychlý Fantastic Examples and Where to Find Them: Compiling Czech Dataset for Evaluating Dictionary Examples 37-46 http://nlp.fi.muni.cz/raslan/2024/paper1.pdf Vojtech Formánek Ondrej Sotolár Quantitative Assessment of Intersectional Empathetic Bias and Understanding 47-57 http://nlp.fi.muni.cz/raslan/2024/paper3.pdf Zuzana Neverilová Hana Zizková Named Entity Alignment in Czech-English Parallel Data 59-64 http://nlp.fi.muni.cz/raslan/2024/paper10.pdf Kristof Anetta Annotating Health Records: Does Ground Truth Even Exist? 65-74 http://nlp.fi.muni.cz/raslan/2024/paper12.pdf
III. Text Corpora
Matús Klestinec Impact of Data Split and Vocabulary Size in Neural Machine Translation for Slovak Language 77-83 http://nlp.fi.muni.cz/raslan/2024/paper7.pdf Jakub Stetina Martin Fajcik Michal Stefánik Michal Hradis A Comparative Study of Text Retrieval Models on DaReCzech 85-100 http://nlp.fi.muni.cz/raslan/2024/paper4.pdf Vlasta Ohlídalová Milos Jakubícek A New Czech Pipeline in Sketch Engine 101-107 http://nlp.fi.muni.cz/raslan/2024/paper15.pdf Maria Khokhlova Natalia Safonova Rubric Extraction for Popular Science Articles in the Russian Language 109-118 http://nlp.fi.muni.cz/raslan/2024/paper14.pdf
IV. NLP Applications
Nataliia Casnochova Zozuk Lívia Kelebercová Dasa Munková Lexical Density in Slovak Speech: A Non-invasive Indicator for Alzheimer’s Disease and Mild Cognitive Impairment 121-128 http://nlp.fi.muni.cz/raslan/2024/paper8.pdf Emma Bednaríková Pavel Rychlý Improvement of Language Identification Processing Speed 129-138 http://nlp.fi.muni.cz/raslan/2024/paper9.pdf Michal Spiegel Ales Horák WebMap: Improving LLM Web Agents with Semantic Search for Relevant Web Pages 139-152 http://nlp.fi.muni.cz/raslan/2024/paper5.pdf Hien Thi Ha Improving Layout Analysis of Scanned Invoices Using Line Detection 153-164 http://nlp.fi.muni.cz/raslan/2024/paper2.pdf