prikaz prve stranice dokumenta Apstraktivno sažimanje teksta pomoću dubokog učenja
No public access
master's thesis
Apstraktivno sažimanje teksta pomoću dubokog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:642515
Škoro, Matej
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Škoro, M. (2021). Apstraktivno sažimanje teksta pomoću dubokog učenja (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:642515

Škoro, Matej. "Apstraktivno sažimanje teksta pomoću dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:642515

Škoro, Matej. "Apstraktivno sažimanje teksta pomoću dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:642515

Škoro, M. (2021). 'Apstraktivno sažimanje teksta pomoću dubokog učenja', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:642515

Škoro M. Apstraktivno sažimanje teksta pomoću dubokog učenja [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 November 04] Available at: https://urn.nsk.hr/urn:nbn:hr:168:642515

M. Škoro, "Apstraktivno sažimanje teksta pomoću dubokog učenja", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:642515

Metadata
TitleApstraktivno sažimanje teksta pomoću dubokog učenja
Title (english)Abstractive Text Summarization Using Deep Learning
AuthorMatej Škoro
MentorMarin Šilić (mentor)
Committee memberMarin Šilić (predsjednik povjerenstva)
Committee memberKlemo Vladimir (član povjerenstva)
Committee memberGoran Delač (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Automatsko sažimanje teksta je područje obrade prirodnog jezika i ima sve veću primjenu i korisnost. Cilj automatskog sažimanja teksta je stvaranje kratke ljudski čitljive verzije izvornog teksta uz izvlačenje i očuvanje najbitnijih informacija. S obzirom na način stvaranja, sažetak može biti ekstraktivan i apstraktivan. Ovaj diplomski rad se prvenstveno bavi algoritmima dubokog učenja koji se koriste za stvaranje apstraktivnih sažetaka. Navedeni su i opisani osnovni načini obrade prirodnog jezika uz usmjeravanje na načine stvaranja sažetaka. U nastavku je detaljno opisan konkretan duboki model za stvaranje apstraktivnog sažetka koji se zasniva na mehanizmu pažnje. Opisani model je programski ostvaren i ugrađen u web primjenski sustav za stvaranje sažetaka ulaznih rečenica. Model je također vrednovan na javno dostupnim skupovima podataka koristeći prikladne mjere te su prikazani dobiveni rezultati.
Abstract (english)
Text summarization is part of the natural language processing field which has wide application and usability. The main goal of text summarization is making shorter human-readable version of the original text while extracting and preserving key information. Given the method of creating, summary can be extractive or abstractive. This thesis is focusing on the deep learning algorithms which are used to make abstractive summaries. The main methods for natural language processing are listed and described while focusing on the methods for text summarization. In continuation, the attention-based deep learning model for generating abstractive summaries is described and implemented. Implemented model is embedded in web application for generating summaries of the input sentences. The model is also tested using online available datasets and appropriate metrics and obtained results are presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:642515
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 on2023-01-13 13:57:07