Thesis Details

Metody extrakce informací

Master's Thesis Student: Adamček Adam Academic Year: 2014/2015 Supervisor: Kouřil Jan, Ing.
English title
Methods of Information Extraction
Language
Czech
Abstract

The goal of information extraction is to retrieve relational data from texts written in natural human language. Applications of such obtained information is wide - from text summarization, through ontology creation up to answering questions by QA systems. This work describes design and implementation of a system working in computer cluster which transforms a dump of Wikipedia articles to a set of extracted information that is stored in distributed RDF database with a possibility to query it using created user interface.

Keywords

information extraction, coreference, NLP, QA, Wikipedia, OpenIE, SECAPI, DECIPHER, NER, RDF, SPARQL, 4store, computer cluster

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology, Field of Study Intelligent Systems
Files
Status
defended, grade A
Date
22 June 2015
Reviewer
Smrž Pavel, doc. RNDr., Ph.D.
Committee
Vojnar Tomáš, prof. Ing., Ph.D. (DITS FIT BUT), předseda
Češka Milan, prof. RNDr., CSc. (DITS FIT BUT), člen
Matoušek Radomil, doc. Ing., Ph.D. (IACS FME BUT), člen
Očenášek Pavel, Mgr. Ing., Ph.D. (DIFS FIT BUT), člen
Peringer Petr, Dr. Ing. (DITS FIT BUT), člen
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Citation
ADAMČEK, Adam. Metody extrakce informací. Brno, 2015. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2015-06-22. Supervised by Kouřil Jan. Available from: https://www.fit.vut.cz/study/thesis/17440/
BibTeX 
@mastersthesis{FITMT17440,
    author = "Adam Adam\v{c}ek",
    type = "Master's thesis",
    title = "Metody extrakce informac\'{i}",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2015,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/17440/"
}

Theses

Back to top