Browsing by Advisor "Mareček, David"
Now showing items 1-7 of 7
-
Analýza a vizualizácia správania jazykového modelu GPT-2
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2022)Date of defense: 7. 6. 2022Visualization of deep neural network models with Transformer architecture is generally a very demanding task which is usually solved by visualizing attention blocks and moni- toring which words these block focus on. However, ... -
Automatic extraction of the main characters from books and their interactions
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2022)Date of defense: 12. 9. 2022The goal of this work is to automatically find named characters in the books, detect all occurrences of these characters and determine places in the text where two or more characters interact together. One of the outputs ... -
Automatic post-editing of phrase-based machine translation outputs
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2013)Date of defense: 20. 5. 2013We present Depfix, a system for automatic post-editing of phrase-based English-to-Czech machine trans- lation outputs, based on linguistic knowledge. First, we analyzed the types of errors that a typical machine translation ... -
Automatický dešifrátor pro šifrovací hry
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2014)Date of defense: 4. 9. 2014Práce se zaměřuje na substituční šifry používané při terénních šifrovacích hrách. Nejprve získáme vzorky jazyka používaného v souvisejících textech a prozkoumáme jeho zvláštnosti. Dále navrhneme jazykový model speciálně ... -
Codenames: a practical application for modelling word association
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2020)Date of defense: 4. 2. 2020Micha de Rijk January 6, 2020 Word association is an important part of human language. Many techniques for capturing semantic relations between words exist, but their ability to model word associations is rarely tested. ... -
Investigating Large Language Models' Representations Of Plurality Through Probing Interventions
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2022)Date of defense: 2. 9. 2022Title: Investigating Large Language Models' Representations Of Plurality Through Probing Interventions Author: Michael Hanna Institute: Institute of Formal and Applied Linguistics Supervisor: RNDr. David Mareček, Ph.D., ... -
Natural language communication with Robots
Defence status: DEFENDED(Univerzita Karlova, Matematicko-fyzikální fakulta, 2017)Date of defense: 7. 9. 2017Interpreting natural language actions in a simulated world is the first step towards robots controlled by natural language commands. In this work we present several models for interpreting unrestricted natural language ...