prikaz prve stranice dokumenta Procjena čitljivosti teksta postupcima obrade prirodnog jezika
No public access
master's thesis
Procjena čitljivosti teksta postupcima obrade prirodnog jezika
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:152447
Injac, Robert
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Injac, R. (2019). Procjena čitljivosti teksta postupcima obrade prirodnog jezika (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:152447

Injac, Robert. "Procjena čitljivosti teksta postupcima obrade prirodnog jezika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:152447

Injac, Robert. "Procjena čitljivosti teksta postupcima obrade prirodnog jezika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:152447

Injac, R. (2019). 'Procjena čitljivosti teksta postupcima obrade prirodnog jezika', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:152447

Injac R. Procjena čitljivosti teksta postupcima obrade prirodnog jezika [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:152447

R. Injac, "Procjena čitljivosti teksta postupcima obrade prirodnog jezika", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:152447

Metadata
TitleProcjena čitljivosti teksta postupcima obrade prirodnog jezika
Title (english)Predicting Text Readability using Natural Language Processing Methods
AuthorRobert Injac
MentorJan Šnajder (mentor)
Committee memberJan Šnajder (predsjednik povjerenstva)
Committee memberVlado Glavinić (član povjerenstva)
Committee memberAnte Đerek (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-11, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Čitljivost teksta je definirana kao lakoća kojom čitatelj može razumjeti pisani tekst. Formule za čitljivost su tradicionalno bile korištene za određivanje čitljivosti teksta. Posljednih godina, ljudi su počeli koristiti methode obrade prirodnog jezika zajedno sa strojnim učenjem za rješavanje ovog problema -- ovo je pristup koji je korišten u ovom radu. Metode obrade prirodnog jezika su korištene za ekstrakciju relevantnih značajki iz teksta. Te značajke su dane na ulaz nekoliko modela zasnovanih na strojnom učenju koji predviđaju razinu čitljivosti. Ti modeli su evaluirani na WeeBit skupu podataka. Uspoređeni su jedan s drugim te s tradicionalnim formulama korištenjem statističkih testova. Testovi su pokazali da modeli zasnovani na strojnom učenju postižu bolje rezultate od tradicionalnih formula za čitljivost.
Abstract (english)
Text readability is defined as the ease with which a reader can understand a written text. Traditionally, readability formulas have been used to determine the readability of a text. In recent years, people have started to use natural language processing (NLP) methods coupled with machine learning to solve this task -- this is the approach used in this work. NLP methods have been used to extract relevant features from a text. These features are given as an input to several machine learning models which predict readability level. The models were evaluated on the WeeBit dataset. They have been compared with each other and with traditional formulas using statistical significance testing. The tests showed that machine learning models outperform traditional readability formulas.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:152447
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 on2020-01-07 18:30:40