prikaz prve stranice dokumenta Extractive Summarization of Scientific Publications
  Download
PDF 1.85 MB
master's thesis
Extractive Summarization of Scientific Publications
Rijeka: University of Rijeka, Faculty of Humanities and Social Sciences, 2019. urn:nbn:hr:186:707042
Krušić, Lucija
University of Rijeka
Faculty of Humanities and Social Sciences

Institutional repository: Repository of the University of Rijeka, Faculty of Humanities and Social Sciences

Cite this document

Krušić, L. (2019). Extractive Summarization of Scientific Publications (Master's thesis). Rijeka: University of Rijeka, Faculty of Humanities and Social Sciences. Retrieved from https://urn.nsk.hr/urn:nbn:hr:186:707042

Krušić, Lucija. "Extractive Summarization of Scientific Publications." Master's thesis, University of Rijeka, Faculty of Humanities and Social Sciences, 2019. https://urn.nsk.hr/urn:nbn:hr:186:707042

Krušić, Lucija. "Extractive Summarization of Scientific Publications." Master's thesis, University of Rijeka, Faculty of Humanities and Social Sciences, 2019. https://urn.nsk.hr/urn:nbn:hr:186:707042

Krušić, L. (2019). 'Extractive Summarization of Scientific Publications', Master's thesis, University of Rijeka, Faculty of Humanities and Social Sciences, accessed 26 June 2024, https://urn.nsk.hr/urn:nbn:hr:186:707042

Krušić L. Extractive Summarization of Scientific Publications [Master's thesis]. Rijeka: University of Rijeka, Faculty of Humanities and Social Sciences; 2019 [cited 2024 June 26] Available at: https://urn.nsk.hr/urn:nbn:hr:186:707042

L. Krušić, "Extractive Summarization of Scientific Publications", Master's thesis, University of Rijeka, Faculty of Humanities and Social Sciences, Rijeka, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:186:707042

Metadata
TitleExtractive Summarization of Scientific Publications
AuthorLucija Krušić
MentorSanda Martinčić-Ipšić (mentor)
Committee memberAna Meštrović (predsjednik povjerenstva)
Committee memberSanda Martinčić-Ipšić (član povjerenstva)
Committee memberMarina Ivašić-Kos (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Humanities and Social Sciences
Rijeka
Defense date and country2019-09-16, Croatia
Scientific / art field,
discipline and subdiscipline		HUMANISTIC SCIENCES
Philology
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Abstract
This Master‟s thesis aims to provide a comprehensive survey of state-of-the art methods used for the task of Automatic Text Summarization. Automatically made summaries can provide great benefits to everyday internet users and enhance the way we search for relevant and necessary information and save time and resources invested in human-made summaries. This thesis provides an overview of the field of ATS and covers the approaches to summarization, the real-world applications of summarization and the various evaluation metrics used to establish the quality of the generated summary. Automatic text summarization is a blooming field which has recently gained significant interest and presently, much advancement is being achieved with the use of neural networks. The thesis will provide a comprehensive survey of the recent work done in the field, including the datasets used and the state-of-the art results of recent studies. The various methods of approaching ATS are described in depth and compared on the basis of their effectiveness.
Abstract (croatian)
Ovaj diplomski rad pruža opsežan pregled najsuvremenijih metoda koje se koriste u polju Automatskog Sažimanja Teksta. Automatski generirani sažeci donose velike prednosti svakodnevnim korisnicima internet te u znatnoj mjeri reduciraju vrijeme i resurse uložene u stvaranje ljudski kreiranih sažetaka. Ovaj rad će pružiti pregled samoga polja i obuhvatiti različite vrste automatskog sažimanja te pružiti uvid u brojne primjene automatskog sažimanja u stvarnome svijetu. Osim toga, biti će opisane metode za evaluaciju generiranih sažetaka koje su se pokazale najprihvatljivijima za određivanje kvalitete generiranih sažetaka. Automatsko sažimanje teksta je polje Računalne obrade prirodnog jezika koje trenutno proživljava novi procvat a napretci u polju se postižu gotovo svakodnevno a osobito u zadnje vrijeme sa sve češćim korištenjem neuronskih mreža za različite zadatke koji spadaju pod obradu prirodnog jezika. Ovaj diplomski rad pružiti će pregled najnovijih istraživanja, što uključuje i zbirke koje se koriste za zadatak automatske sumarizacije kao i najsuvremenije i najuspješnije modele te njihove rezultate. Raznolike metode pristupanja automatskom sažimanju teksta su detaljno opisane i uspoređene na temelju njihove funkcionalnosti i uspješnosti.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:186:707042
Study programmeTitle: English Language and Literature (double major); specializations in: Teaching Track
Course: Teaching Track
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra edukacije engleskog jezika i književnosti (magistar/magistra edukacije engleskog jezika i književnosti)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Public noteDrugi studijski program je informatika.
Created on2020-06-25 10:26:15