Strojno učenje za sintezu sažetaka teksta

undergraduate thesis

• Title (english): A Machine-learning Based Model for Text Summarization
• Author: Valentina Fatorić
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Petra Bevandić (član povjerenstva)
• Committee member: Ivan Krešo (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu je opisan problem automatskog sažimanja teksta i dva različita pristupa tom problemu: ekstraktivno i apstraktivno sažimanje. Za ekstraktivno sažimanje su opisane različite metode koje se koriste za izdvajanje najbitnijih rečenica, a za apstraktivno je objašnjeno kako je strojevima omogućeno parafrazirati pomoću strojnog učenja i povratnih neuronskih mreža. Također, u ovom radu su objašnjene različite mjere ocjenjivanja generiranih sažetaka te je napravljena implementacija i usporedba rezultata oba pristupa.

Abstract (english)

This thesis describes the problem of automatic text summarization and two different approaches to this problem: extractive and abstractive summarization. For extractive summarization various methods are used for extracting the most important sentences and for abstractive summarization it is explained how machines can paraphrase by using machine learning and recurrent neural networks. In this thesis are also explained different evaluation measures for generated summaries and are made implementations and comparisons of the results of both approaches.

• Keywords: sažetak; ekstraktivno; apstraktivno; strojno učenje; povratne neuronske mreže; mreže duge kratkoročne memorije; mjere ocjenjivanja
• Keywords (english): summary; extractive; abstractive; machine learning; recurrent neural network; long short-term memory; evaluation measures
• Language: croatian
• URN:NBN: urn:nbn:hr:168:079743
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 20:11:42