Thesis Details

Extrakce sémantických vztahů z textu

Master's Thesis Student: Schmidt Marek Academic Year: 2007/2008 Supervisor: Smrž Pavel, doc. RNDr., Ph.D.
English title
Extraction of Semantic Relations from Text
Language
Czech
Abstract

Extraction of semantic relations from English text is the topic of this thesis. It focuses on exploitation of a dependency parser. A method based on syntactic patterns is proposed and evaluated in addition to evaluation of several statistical methods over syntactic features. It applies the methods for extraction of a hypernymy relation and evaluates it on the WordNet thesaurus. A system for extraction of semantic relations from text is designed and implemented based on these methods.

Keywords

extraction of semantic relations, term extraction, text mining, ontology learning, ontology, natural language processing

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology, Field of Study Computer Graphics and Multimedia
Files
Status
defended, grade A
Date
19 June 2008
Reviewer
Burget Radek, doc. Ing., Ph.D.
Committee
Češka Milan, prof. RNDr., CSc. (DITS FIT BUT), předseda
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT), člen
Kršek Přemysl, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Orság Filip, Ing., Ph.D. (DITS FIT BUT), člen
Sojka Eduard, doc. Dr. Ing. (VŠB-TUO), člen
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT), člen
Citation
SCHMIDT, Marek. Extrakce sémantických vztahů z textu. Brno, 2008. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2008-06-19. Supervised by Smrž Pavel. Available from: https://www.fit.vut.cz/study/thesis/4259/
BibTeX 
@mastersthesis{FITMT4259,
    author = "Marek Schmidt",
    type = "Master's thesis",
    title = "Extrakce s\'{e}mantick\'{y}ch vztah\r{u} z textu",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2008,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/4259/"
}

Theses

Back to top