prikaz prve stranice dokumenta Označavanje vrsta riječi pomoću neuronskih mreža
  Download
PDF 3.82 MB
master's thesis
Označavanje vrsta riječi pomoću neuronskih mreža
Split: University of Split, Faculty of Science, 2022. urn:nbn:hr:166:035081
Juričić, Josipa
University of Split
Faculty of Science
Department of Informatics

Cite this document

Juričić, J. (2022). Označavanje vrsta riječi pomoću neuronskih mreža (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:035081

Juričić, Josipa. "Označavanje vrsta riječi pomoću neuronskih mreža." Master's thesis, University of Split, Faculty of Science, 2022. https://urn.nsk.hr/urn:nbn:hr:166:035081

Juričić, Josipa. "Označavanje vrsta riječi pomoću neuronskih mreža." Master's thesis, University of Split, Faculty of Science, 2022. https://urn.nsk.hr/urn:nbn:hr:166:035081

Juričić, J. (2022). 'Označavanje vrsta riječi pomoću neuronskih mreža', Master's thesis, University of Split, Faculty of Science, accessed 16 May 2024, https://urn.nsk.hr/urn:nbn:hr:166:035081

Juričić J. Označavanje vrsta riječi pomoću neuronskih mreža [Master's thesis]. Split: University of Split, Faculty of Science; 2022 [cited 2024 May 16] Available at: https://urn.nsk.hr/urn:nbn:hr:166:035081

J. Juričić, "Označavanje vrsta riječi pomoću neuronskih mreža", Master's thesis, University of Split, Faculty of Science, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:166:035081

Please login to the repository to save this object to your list.
Metadata
TitleOznačavanje vrsta riječi pomoću neuronskih mreža
Title (english)Part-of-speech tagging of the Croatian language with neural networks
AuthorJosipa Juričić
MentorBranko Žitko (mentor)
Committee memberBranko Žitko (predsjednik povjerenstva)
Committee memberAni Grubišić (član povjerenstva)
Committee memberInes Šarić-Grgić (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2022-09-28, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Označavanje vrsta riječi jedan je od temeljnih zadataka u području obrade prirodnog jezika. Ono samo po sebi ne rješava određeni problem u obradi prirodnog jezika, ali je preduvjet za mnoge druge procese kao što su analiza sentimenta, prevođenje teksta ili prepoznavanje govora. Označavanja temeljena na pravilima, transformacijama ili stohastičkim metodama opisana su i uspoređena sa korištenjem neuronskih mreža u svrhu označavanja vrsta riječi. Implementirane su RNN i LSTM arhitekture neuronske mreže čiji modeli mogu provoditi automatsko označavanje vrsta riječi za dani tekst pisan hrvatskim jezikom. Kako bi se utvrdila efikasnost uporabe modela neuronske mreža za ovakav zadatak, modeli su testirani i evaluirani. Cilj je prikazati primjenu neuronskih mreža za razvoj označivača vrsta riječi hrvatskog jezika.
Abstract (english)
Part-of-speech tagging is one of the main tasks of natural language processing. On its own, it does not solve a specific problem of natural language processing but it is a part of preprocessing in sentiment analysis, text translation or speech recognition. In the first part of this thesis the rule-based, transformation based and stochastic methods of part-of-speech tagging are described and compared to neural network methods. As a practical part of the thesis, RNN and LSTM neural network models are implemented for an automatic part-of-speech tagger of the Croatian language. To check the efficiency of using the neural network approach for this task, models are tested and evaluated. The aim of this thesis is to implement neural networks for an automatic part-of-speech tagger of the Croatian language.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:035081
Study programmeTitle: Computer Science; specializations in: major in teaching
Course: major in teaching
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra edukacije informatike (magistar/magistra edukacije informatike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution-NoDerivatives 4.0 International (CC BY-ND 4.0) icon
RepositoryRepository of Faculty of Science
Created on2023-02-16 14:06:19