This paper attempts to compare between the advancements in the productivity of Arabic into English Machine Translation Systems between two years, 2008 and 2013. It also aims to evaluate the progress achieved by various systems of Arabic into English electronic translation between the two years. For tracing such advancement, a comparative analysis of translated texts taken from previous studies were re-evaluated according to certain criteria by focusing on the functional characteristics and sub-characteristics of the output: reliability, fidelity, terminology, and syntax. This re-evaluation proposes to develop metrics related to these four functional criteria. The data used in this study are the same five text-genres that have been evaluated by one of the researchers in 2008 that covered technical, legal, literary, journalistic, and economic topics translated from Arabic into English using seven Machine Translation systems: Google, Ajeeb, Professional Translator, 1-800-translate, World lingo, Tran Sphere, and An-Nakel. The translated texts were analyzed to identify errors, deficiencies, limitations, and loss of meaning. Results of this analysis were compared with those findings achieved in 2008 so as to bring together complementary innovative progress in the production of Machine Translation. The findings revealed certain advancement in the translated production of Google system compared with the deficiencies of the other six systems in all the functional characteristics of the output.
Key words: Machine translation evaluation, Arabic into English translation, functional characteristics of output.
Copyright © 2022 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0