Thesis Details

Umělý básník

Bachelor's Thesis Student: Bančák Michal Academic Year: 2016/2017 Supervisor: Beneš Karel, Ing.
English title
Artificial Poet
Language
Czech
Abstract

The paper presents a work on automatic poetry generation using the Long Short-TermMemory recurrent neural network. The aim of this work is to create an application thatimitates the writing of poems. This is a character-level language modeling in the Slovaklanguage. The neural network model used in the work consists of three layers of LSTM,with 400 hidden units. A collection of poems in the Slovak language with a size of 900k characters was also created for this work. . The final model is generating text that has poemelements. Achieved accuracy of generation is 41.85%.

Keywords

Neural Network, Long Short-Term Memory, Automatic Poem Generation, Character-Level Language modeling

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade D
Date
16 June 2017
Reviewer
Szőke Igor, Ing., Ph.D.
Committee
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT), předseda
Bidlo Michal, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Hliněná Dana, doc. RNDr., Ph.D. (DMAT FEEC BUT), člen
Rozman Jaroslav, Ing., Ph.D. (DITS FIT BUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Citation
BANČÁK, Michal. Umělý básník. Brno, 2017. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2017-06-16. Supervised by Beneš Karel. Available from: https://www.fit.vut.cz/study/thesis/19363/
BibTeX 
@bachelorsthesis{FITBT19363,
    author = "Michal Ban\v{c}\'{a}k",
    type = "Bachelor's thesis",
    title = "Um\v{e}l\'{y} b\'{a}sn\'{i}k",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2017,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/19363/"
}

Theses

Back to top