Thesis Details

Strojové učení pro odpovídání na otázky v češtině

Master's Thesis Student: Pastorek Peter Academic Year: 2019/2020 Supervisor: Smrž Pavel, doc. RNDr., Ph.D.
Language
Slovak
Abstract

This Master's thesis deals with teaching neural network question answering in Czech. Neural networks are created in Python programming language using the PyTorch library. They are created based on the LSTM structure. They are trained on the Czech SQAD dataset. Because Czech data set is smaller than the English data sets, I opted to extend neural networks with algorithmic procedures. For easier application of algorithmic procedures and better accuracy, I divide question answering into smaller parts.

Keywords

machine learning, neural network, natural language processing, question answering

Department
Degree Programme
Information Technology, Field of Study Information Systems
Files
Status
defended, grade E
Date
16 July 2020
Reviewer
Committee
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), předseda
Bartík Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Chudý Peter, doc. Ing., Ph.D. MBA (DCGM FIT BUT), člen
Peringer Petr, Dr. Ing. (DITS FIT BUT), člen
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
Citation
PASTOREK, Peter. Strojové učení pro odpovídání na otázky v češtině. Brno, 2020. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-16. Supervised by Smrž Pavel. Available from: https://www.fit.vut.cz/study/thesis/22913/
BibTeX
@mastersthesis{FITMT22913,
    author = "Peter Pastorek",
    type = "Master's thesis",
    title = "Strojov\'{e} u\v{c}en\'{i} pro odpov\'{i}d\'{a}n\'{i} na ot\'{a}zky v \v{c}e\v{s}tin\v{e}",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2020,
    location = "Brno, CZ",
    language = "slovak",
    url = "https://www.fit.vut.cz/study/thesis/22913/"
}
Back to top