Aleš Manuel Papáček

Main Research Interests

LLMs, RAG, Machine Translation, Etymology, Morphology

 

Projects

CZDEMOS4AI - A beneficial multi-agent AI avatar in a small democratic society. 

• Project to create "AI avatars" (LLM with RAG) for various topics (history, law, media-security, psychic well being)
• I focus on evaluation of model outputs

Universal Segmentations - collection of lexical resources that captures morphological segmentations, harmonized into a cross-linguistically consistent annotation scheme.

Identifing Indo European roots in Czech words

Morph Origin Identification - etymology on level of individual morphs rather than whole words

Curriculum Vitae

2025-... Mgr. in Arteficial Inteligence, MFF UK

2022-2025 Bc. in Computer Science (specialization: Artificial Intelligence), MFF UK

Teaching

NMAI059 - Probability and Statistics 1

• Summer semester 2026
• Information for students

Selected Bibliography

• Google Scholar
• ORCID: 0009-0000-3801-0819

Publications:

1. Aleš Manuel Papáček, Zdeněk Žabokrtský (2026): Tracing Morph Origins in Czech: A Computational Approach to Morph-Level Etymology. In: LREC 2026 | Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026 Workshop Proceedings, pp. 7-17, anguage Resources Association (ELRA), Paris, France, ISBN 978-2-493814-58-6 (url, bibtex)

Datasets/software:

1. Vojtěch John, Zdeněk Žabokrtský, Benjamin Reeves, Magda Ševčíková, Haridanmu Abdukerim, Abduhalik Abduwaiti, Abdukerim Abliz, Ebrahim Ansari, Timofey Arkhangelskiy, Lizaveta Astapenka, Niyati Bafna, Khuyagbaatar Batsuren, Gábor Bella, Pier Marco Bertinetto, Chiara Celata, Hélène Deacon, Konstantinos Diamantopoulos, Šárka Dohnalová, Alexei Fedorenko, Matea Filko, Antonín Forst, Federica Gamba, Timur Garipov, Tanja Gaustad, Fausto Giunchiglia, Anna Glazkova, Hamid Haghdoost, Irina Khomchenkova, Victoria Khurshudyan, Maria Klyucheva, Lukáš Kyjánek, Eleonora Litta, Olga Lyashevskaya, Joël Macoir, Hugo Mailhot, Sun Maosong, Cindy McKellar, Maria Medvedeva, Dmitry Morozov, S. N. Muralikrishna, Fiametta Namer, Anna Nedoluzhko, Mahshid Nikravesh, Aleš Manuel Papáček, Marco Passarotti, Alexey Polyakov, Mihail Potapov, Mishra Pruthwik, Chrysanthi Raftopoulou, Ashwath B. Rao, Husain Samar, Claudia Sánchez-Gutiérrez, Iurii Savelev-Galiaminskii, Dipti Misra Sharma, Eleonora Slavíčková, Abishek Stephen, Emil Svoboda, Krešimir Šojat, Vanja Štefanec, Luigi Talamo, Jonáš Vidra, Arseniy Vydrin, Maximiliano Wilson, Aigul Zakirova, Yang Liu (2026): Universal Segmentations 1.5 (DataSW). (url)
2. Michal Olbrich, Viktória Kovács, Šárka Dohnalová, Vojtěch John, Lukáš Kyjánek, Aleš Manuel Papáček, Emil Svoboda, Magda Ševčíková, Jonáš Vidra, Zdeněk Žabokrtský (2025): DeriNet 2.3 (DataSW). (url)