Algorithms for identifying terms in text

Mag Elizaveta Iuldasheva

Bakalářská práce

Abstract:

The main aim of the thesis is to understand the underlying principles of terminology extractionas a subfield of Information extraction as well as to study the necessary requirements needed forcreating algorithms in this sphere. Additional aim of the work presented is to study the workflowprocess of already existing algorithms and create the algorithm for terminology extraction.In the research there will be observed the main tendencies in the field of InformationExtraction, analyzed the main tools and technologies and chosen the most suitable ones. Based on theresearch, the most appropriate techniques will be included in the creation of the term extractionalgorithm. The methodology used in this work includes literature overview in the theoretical part andcase study and creation of algorithms workflow mock up in the practical part.

Keywords

Algorithm, Natural language processing, Computational linguistics, Text analysis, Entities recognition

Jazyk práce: angličtina

Datum vytvoření / odevzdání či podání práce: 13. 3. 2018

Obhajoba závěrečné práce

• Vedoucí: Ing. Jiří Brožek, Ph.D.

Česká zemědělská univerzita v Praze

Provozně ekonomická fakulta

Bakalářský studijní program / obor:
Systems Engineering and Informatics / Informatics