Open AccessEvaluation of Google Image Translate in Rendering Arabic Signage into English
Author(s) -
Zakaryia Almahasees,
Sameh Mahmoud
Publication year - 2022
Publication title -
world journal of english language
Language(s) - English
Resource type - Journals
eISSN - 1925-0711
pISSN - 1925-0703
DOI - 10.5430/wjel.v12n1p185
Subject(s) - computer science , rendering (computer graphics) , lexis , arabic , artificial intelligence , natural language processing , information retrieval , linguistics , philosophy
When people travel to another country for work or leisure, they regularly need a medium to help them understand the written messages in other languages. Google Translate offers a new service: translating the content of images (texts) instantly and freely into 100 languages powered by the Neural Machine Translation approach (NMT). In this vein, the current research paper attempts to evaluate the accuracy of Google Image Translate service in rendering the texts printed on Arabic signage: banners and road and shop signs from Arabic into English. Besides, it aims to identify the capacity of Google Translate in rendering Arabic signage into English effectively without the help of human translators. The paper adopts the Linguistic Error Analysis Framework of Costa et al. (2015) in analyzing the output of Google image service in terms of orthography, grammar, lexis, and semantics. The paper shows that Google Translate made the following errors while rendering the content of images into English: mistranslation, omission, additions, wrong choice, misordering, subject-verb disagreement, and semantic errors. In conclusion, the Google Image Translate service helps the users configure the gist of the image. However, a human translator is still needed since MT may not provide an adequate and effective translation as humans do.