prikaz prve stranice dokumenta Kontekstna provjera pravopisa temeljena na n-gramima
No public access
master's thesis
Kontekstna provjera pravopisa temeljena na n-gramima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. urn:nbn:hr:168:789335
Srdić, Ivan
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Srdić, I. (2017). Kontekstna provjera pravopisa temeljena na n-gramima (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:789335

Srdić, Ivan. "Kontekstna provjera pravopisa temeljena na n-gramima." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:789335

Srdić, Ivan. "Kontekstna provjera pravopisa temeljena na n-gramima." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:789335

Srdić, I. (2017). 'Kontekstna provjera pravopisa temeljena na n-gramima', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:789335

Srdić I. Kontekstna provjera pravopisa temeljena na n-gramima [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2017 [cited 2024 December 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:789335

I. Srdić, "Kontekstna provjera pravopisa temeljena na n-gramima", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:168:789335

Metadata
TitleKontekstna provjera pravopisa temeljena na n-gramima
Title (english)Contextual Spellchecking Based on N-grams
AuthorIvan Srdić
MentorGordan Gledec (mentor)
Committee memberGordan Gledec (predsjednik povjerenstva)
Committee memberDamir Kalpić (član povjerenstva)
Committee memberBoris Vrdoljak (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2017-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu prikazano je da je, neovisno o složenosti hrvatskog jezika, moguće napraviti sustav za ispravak kontekstnih grešaka. Podjelom sustava na komponente omogućena je jednostavna nadogradnja postojeće implementacije. Korištenjem dobro poznatih klasifikatora i procjenitelja frekvencije s manjim optimizacijama i podjelom grešaka u confusion setove dobiven je sustav za kontekstnu provjeru pravopisa koji na primjeru korištenom u radu ima visoki F_1 = 0.95.
Abstract (english)
In this thesis it was shown that it is possible to create a system for contextual spellchecking regardless of the complexity of the Croatian language. Simple upgrading of the existing implementation was achieved by separating the system into several components. Using a well known classifier and frequency estimator with smaller tweaks and by separating errors into confusion sets resulted in a contextual spellchecking system which had a high score of F_1 = 0.95 on the example examined in the thesis.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:789335
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-14 00:53:24