Razan Khasawneh, Bilal Alsharif
This study is a quantitative analysis that investigates and compares the quality level of Computer Assisted Translation (CAT) tools, Neural Machine Translation (NMT) systems, and Large Language Models (LLMs) against each other and how well they can perform on translation tasks from English into Arabic and vice versa, in comparison to human translator. By utilizing a Bilingual Evaluation Understudy (BLEU) and comparing seven translation platforms, the study revealed that AI models outperform both CAT tools and NMT systems when translating in both directions. In addition, Gemini scores the highest BLEU score in both directions, surpassing all the other six platforms, while Google Translate scores are the lowest. The study also reveals that these platforms struggle more with English-to-Arabic translation due to the complexity of the Arabic language. Since CAT tools generally have the lowest scores, they assist the human translator rather than replacing them, providing a partially automated translation. Accordingly, AI models can be more helpful and preferable due to their high BLEU score. However, despite often producing accurate translations and conveying the core meaning, MT may still struggle to imitate the stylistic choices and conciseness that characterize a professional human translator at work.