prikaz prve stranice dokumenta Usporedna analiza alata za strojno prevođenje
  Download
PDF 646.78 KB
master's thesis
Usporedna analiza alata za strojno prevođenje
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. urn:nbn:hr:200:022640
Popadić, Dragana
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Popadić, D. (2017). Usporedna analiza alata za strojno prevođenje (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:022640

Popadić, Dragana. "Usporedna analiza alata za strojno prevođenje." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:200:022640

Popadić, Dragana. "Usporedna analiza alata za strojno prevođenje." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:200:022640

Popadić, D. (2017). 'Usporedna analiza alata za strojno prevođenje', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 26 March 2025, https://urn.nsk.hr/urn:nbn:hr:200:022640

Popadić D. Usporedna analiza alata za strojno prevođenje [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2017 [cited 2025 March 26] Available at: https://urn.nsk.hr/urn:nbn:hr:200:022640

D. Popadić, "Usporedna analiza alata za strojno prevođenje", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:200:022640

Please login to the repository to save this object to your list.
Metadata
TitleUsporedna analiza alata za strojno prevođenje
Title (english)Comparative analysis of machine translation tools
AuthorDragana Popadić
MentorIrena Galić (mentor)
MentorDragana Božić Lenard (mentor)
Committee memberIrena Galić (predsjednik povjerenstva)
Committee memberČaslav Livada (član povjerenstva)
Committee memberDragana Božić Lenard (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2017-10-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
U svijetu globalizacije gdje je sve veća potreba za internacionalizacijom, također raste i potreba za prevoditeljskim uslugama. Ljudski je prevoditelj zbog svojih kompetencija nezamjenjiv, no budući da vremenski čimbenik igra veliku ulogu, korištenje informacijsko-komunikacijske tehnologije predstavlja značajnu potporu i zasigurno ubrzava proces i isporuku prijevoda. Rad započinje definiranjem nužnih pojmova iz područja strojnoga prevođenja i ukazivanjem na važnost automatizacije procesa... More prevođenja. Objašnjene su najvažnije karakteristike strojnoga prevođenja i dan je kratki povijesni pregled razvoja strojnoga prevođenja. Za potrebe ovoga diplomskoga rada, odabrana su tri besplatna alata za strojno prevođenje Google Translate, Bing Translator i Yandex Translate kojima su analizirane tri tematski različite vrste radova – izvorno-znanstveni članak, popularno-znanstveni članak i novinski članak. Svi članci obrađuju neku od podtema računarstva. Metodom nasumičnoga odabira, izabrano je 15 rečenica koje su, nakon prijevoda svih triju alata za strojno prevođenje, analizirane na morfološkoj, sintaktičkoj, semantičkoj i leksičkoj razini. Rezultati analize pokazuju kako je najprecizniji alat za strojno prevođenje Google Translate, dok je najbolje prevedeni tekst izvorno-znanstveni rad. Razlog tome jest tipična ustaljenost jezičnoga izražavanja bez učestalih uporaba frazalnih glagola, kolokacijskih i idiomatskih struktura koje su zahtjevne i često problematične za prijevod. Za njih se u obzir mora uzeti i kontekst te imati više znanja od poznavanja dvaju jezika, odnosno enciklopedijsko ili znanje o svijetu, što alati za strojno prevođenje nemaju. Less
Abstract (english)
Globalization has resulted in internationalization of written discourse and consequently a growing need for translating services. Due to his competencies, a translator is irreplaceable. However, since short deadlines are significant factors in translating, the use of information and communication technologies is of utmost importance and provides a considerable support thus speeding up the process of translation. The paper starts with defining a machine translation terminology and... More pointing to the importance of automizing the translation process. The most important characteristics of machine translation are elaborated on followed by a short developmental overview of machine translation. For the purpose of this paper, three free tools for machine translation, namely Google Translate, Bing Translator and Yandex Translate are selected. The tools are used to translate three types of papers – an original research paper, a popular-scientific paper and a newspaper article. All three papers deal with issues in the field of computer science. Using a simple random sampling method, 15 sentences were selected to be analyzed on a morphological, syntactical, semantical and lexical level. The results point to Google Translate being the most efficient machine translation tool and the best translated text is the original scientific paper. The latter result may be explained with a typical scientific linguistic expression containing fewer phrasal verbs, collocations and idiomatic structures all of which are challenging and problematic for translation. To paraphrase, one needs to consider the context of such sentences and demonstrate more than solely the knowledge of two languages, i.e. one needs to acquire encyclopedic knowledge, which tools for machine translation are unable to gain. Less
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:022640
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
RepositoryFaculty of Electrical Engineering, Computer Science and Information Technology Osijek
Created on2017-11-13 15:16:26
accessibility

closeAccessibilityrefresh

If you wish to permanently save changes, click on Save, if not - your settings will be reset when you restart the browser.