Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal English Language and Literature International Conference (ELLiC) Proceedings
Arif Muttaqin Rusadi
Universitas Sanata Dharma
Languange, Linguistic, Communication & Media

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
EVALUATING THE ACCURACY OF GOOGLE TRANSLATE AND CHATGPT IN TRANSLATING WINDOWS 11 EDUCATION INSTALLATION GUI TEXTS TO INDONESIAN: AN APPLICATION OF KOPONEN’S ERROR CATEGORY Arif Muttaqin Rusadi; Harris Hermansyah Setiajid
English Language and Literature International Conference (ELLiC) Proceedings Vol 6 (2023): Transforming Paradigm, Diversity, and Challenges in English Language Learning, Linguis
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Understanding computer systems in a foreign language can be challenging, leading users to rely on machine translation tools to overcome language barriers. However, the effectiveness of these tools varies, so it is crucial to assess their performance. This study aims to evaluate the translation accuracy of two popular machine translations, Google Translate and ChatGPT, by examining the errors they produce. The research uses Koponen's translation error category. The study focuses on translating the installation GUI texts of Windows 11 Education into Indonesian. The main objective is to determine the error categories and their distribution in the translations created by Google Translate and ChatGPT. The findings will help developers improve their translation algorithms and guide users in choosing the most appropriate translation system for specific situations, especially when dealing with computer systems. The research identified five error categories from six categories proposed by Koponen in the translations generated by Google Translate and ChatGPT. A total of 29 errors were found, distributed as follow: omitted concepts (17.24%), added concepts (24.13%), untranslated concepts (20.68%), mistranslated concepts (3.44%), and substituted concept (34.48%). In term of relation error only one type is found, that is added participant. This study provides valuable insights into the performance of widely used machine translation tools in real-world situations, emphasizing areas for improvement to enhance their accuracy and reliability, ultimately benefiting both developers and end-users.
Co-Authors Harris Hermansyah Setiajid