Mgr. Michal Štefánik

Doctoral thesis

Axes of Robustness of Neural Language Models

Axes of Robustness of Neural Language Models
Abstract:
V posledných rokoch sa jazykové modely stali technológiou používanou v širokej škále aplikácií, presahujúcej tradičné úlohy spracovania prirodzeného jazyka. Vďaka svojej všestrannosti a prispôsobivosti predstavujú moderné jazykové modely základ systémov zahŕňajúcich viackrokové uvažovanie, interaktívne konverzácie alebo rozhodovacie systémy. Aplikácie, ktoré stoja na neurónových jazykových modeloch …more
Abstract:
In recent years, language models have emerged into a technology adopted in a wide variety of applications, nowadays largely exceeding traditional natural language processing tasks. Thanks to their versatility and adaptability, modern language models nowadays present a backbone for systems involving multistep reasoning, interactive conversations or decision-making agents. However, together with benefits …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 5. 9. 2024

Thesis defence

  • Date of defence: 6. 2. 2025
  • Supervisor: doc. RNDr. Petr Sojka, Ph.D.
  • Reader: prof. Pontus Lars Erik Saito Stenetorp, PhD, prof. Jörg Tiedemann, PhD

Citation record

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky

Masaryk University

Faculty of Informatics

Doctoral programme / field:
Computer Science / Fundamentals of Computer Science

Theses on a related topic

  • No theses on a related topic available.