Automatsko sažimanje teksta

undergraduate thesis

• Title (english): Automatic text summarization
• Author: Helena Viher
• Mentor: Kristina Kocijan (mentor)
• Committee member: Vjera Lopina (predsjednik povjerenstva)
• Committee member: Ivan Dunđer (član povjerenstva)
• Committee member: Kristina Kocijan (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2018-09-25, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

Automatsko sažimanje teksta podrazumijeva stvaranje sažetka uz pomoć računalnih algoritama koji iz dokumenata izlučuju samo najrelevantnije rečenice. Cilj ovog rada je prikazati razvoj automatskog sažimanja, pristupe koji se koriste pri stvaranju sažetka, tj. ekstrakciju i apstrakciju te načine evaluacije dobivenog rezultata kako bi se osigurala njegova kvaliteta te poboljšao rad samih algoritama. Naglašava se njegova važnost u raznim područjima zbog progresivno sve veće količine podataka koje nije moguće ručno obraditi, a također se prikazuju problemi koji se javljaju pri sažimanju te kako se s njima suočiti.

Abstract (english)

Automatic text summarization is defined as a process of creating abstract using computer algorithms that extract only the most relevant sentences from a given document. Main purpose of this thesis is to review development of automatic summarization over the years, text summarization approaches, i.e. extraction and abstraction and evaluation methods of automatic summaries which are important part of quality insurance and help improve summarization. Thesis also focuses on importance of automatic text summarization in different fields caused by ever-growing amount of data that's impossible for humans to process without help of computers. Problems that appear during text summarization are also mentioned and solutions to these problems are suggested.

• Keywords: automatsko sažimanje teksta; sažimanje; obrada prirodnog jezika; ekstrakcija; apstrakcija; evaluacija sažetaka
• Keywords (english): automatic text summarization; summarization; natural language processing; extraction; abstraction; summary evaluation
• Language: croatian
• URN:NBN: urn:nbn:hr:131:196830
• Study programme: Title: Information Sciences; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-12-10 12:54:09