Razumevati nevronščino: Kako si ljudje razlagamo jezik strojnih prevajalnikov

Bordon, David (author), Vintar, Špela (mentor)

V magistrski nalogi preverjam razumljivost nerevidiranih strojno prevedenih spletnih besedil pri končnih uporabnikih. Raziskavo sem izvedel z anketo, ki je vsebovala primere strojnih prevodov splošnih besedil, ki sem jih prevedel s prevajalnikoma Google Translate in eTranslation. Primeri vključevali napake štirih vrst, ki so bile predstavljene v kontekstu. Ta je lahko bil izključno besedilni, kombinacija besedilnega in vizualnega dveh vrst – s slikovnim gradivom, ki vpliva na razumevanje ali ne – ali vezan na pravilen izbor slike, na katero se besedilo nanaša. Vzorec 120 anketirancev je pokazal približno 59 % stopnjo razumevanja primerov, rezultati pa so bili boljši v kategorijah, kjer je bilo razumevanje vezano na slikovno gradivo oz. na izbor pravilne slike.

• Language: Slovenian
• Keywords: razumevanje strojnih prevodov, nevronsko strojno prevajanje (NMT), nerevidirani prevodi, nevronščina, končni uporabniki
• Work type: Master's thesis/paper
• Organization: FF - Faculty of Arts
• Year: 2021
• PID: 20.500.12556/RUL-125328
• Publication date in RUL: 11.03.2021

BORDON, David, 2021, Razumevati nevronščino: Kako si ljudje razlagamo jezik strojnih prevajalnikov [online]. Master’s thesis. [Accessed 23 April 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=125328

Secondary language

• Language: English
• Title: Comprehending the neural language: How people understand the language of machine translation engines

Abstract

This thesis tackles the issue of end-user comprehensibility of unedited machine translated web texts. The research was carried out by using a questionnaire, which contained examples of general texts, translated with Google Translate and eTranslation. The examples included four different types of errors, which were presented in context. The latter was either purely textual, a combination of textual and visual of two types – with pictures that affected comprehension or did not – or linked to the correct selection of a picture the text referred to. A sample of 120 respondents showed a comprehensibility rate of roughly 59 %, while the results were better in the categories where comprehensibility was tied to the visual material or the correct selection of an image.

• Keywords: machine translation comprehensibility, neural machine translation (NMT), unedited texts, neural language, end-users