Prepoznavanje i grupiranje digitalnih sadržaja temeljeno na semantici

master's thesis

• Title (english): Recognition and grouping of digital contents based on semantic
• Author: Sandro Pribolšan
• Mentor: Dragan Jevtić (mentor)
• Committee member: Dragan Jevtić (predsjednik povjerenstva)
• Committee member: Mirko Randić (član povjerenstva)
• Committee member: Miljenko Mikuc (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-03, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu analizirani se modeli temeljeni na statistikama i modeli temeljeni na strojnom učenju koji su pogodni za obradu tekstualnih digitalnih sadržaja. Kroz rad se obradila obrada prirodnog jezika, automatizirano prolanaženje pojmova u jednostavnom tekstu, izrada grafa semantičkih odnosa, semantička sličnost dvaju tekstova, te rad u alatu Tropes.

Abstract (english)

In this work models based on statistics and models based on machine learning that are suitable for processing text digital content were processed. Through the work it has also been processed natural language processing, automatic concept extraction from plain text, semantic relationship graph, semantic similarity of the two texts, and work in the tool Tropes.

• Keywords: obrada prirodnog jezika; strojno učenje; statistika; grupiranje; prepoznavanje; semantika; graf semantičkih odnosa; tekst; jezični modeli
• Keywords (english): natural language processing; machine learning; statistics; grouping; recognition; semantics; semantic relationships graph; text; language models
• Language: croatian
• URN:NBN: urn:nbn:hr:168:863222
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 11:26:33