Problem leksičke višeznačnosti u obradi prirodnog jezika

undergraduate thesis

• Title (english): Problems of lexical polysemy in natural language processing
• Author: Ivana Sara Žordić
• Mentor: Nives Mikelić Preradović (mentor)
• Committee member: Petra Bago (predsjednik povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2019-09-23, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

U ovom se radu definiraju tipovi višeznačnosti s naglaskom na leksičkoj višeznačnosti i podtipovima leksičke višeznačnosti u obradi prirodnog jezika. Definirani se pojmovi oprimjeruju i problematiziraju paralelno koristeći se hrWaC-om, Hrvatskim jezičnim portalom (HJP-om) i CROVALLEX-om te se uspoređuju rezultati hrWaC-a i HJP-a i dovode se u korelaciju s rezultatima Google prevoditelja. Ističu se glavni problemi višeznačnosti i uzroci 'pogrešnih' rezultata pretraga Google prevoditelja i... More hrenWaC-a. Less

Abstract (english)

This paper defines the types of ambiguity with emphasis on lexical polysemy and ambiguities and its subtypes in Natural Language Processing (NLP). These concepts are problematized and compared using Croatian Web Corpus (hrWaC), Croatian Language Portal and CROVALLEX. Furthermore, the Google Translator and hrenWaC errors in translation are analyzed and associated with problems of different types of ambiguities.

• Keywords: višeznačnost; obrada prirodnog jezika; leksička višeznačnost; fonološka višeznačnost; morfološka višeznačnost; sintaktička višeznačnost; semantička višeznačnost; strojno prevođenje; Google Prevoditelj; hrWaC; hrenWaC; CROVALLEX
• Keywords (english): polysemy; ambiguity; Natural Language Processing; lexical ambiguity; phonological ambiguity; morphological ambiguity; syntactic ambiguity; semantic ambiguity; machine translation; Google Translate; hrWaC; hrenWaC; CROVALLEX
• Language: croatian
• URN:NBN: urn:nbn:hr:131:674803
• 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: Access restricted to authenticated users
• Created on: 2020-09-12 16:06:09