First Result on Arabic Neural Machine Translation
This work addresses the lack of research on neural machine translation for Arabic, a non-European language, though it is incremental as it applies existing methods to a new language pair.
The authors applied neural machine translation to Arabic-English translation, finding that it performs comparably to phrase-based systems on in-domain data but significantly outperforms them on out-of-domain test sets, making it more suitable for real-world use.
Neural machine translation has become a major alternative to widely used phrase-based statistical machine translation. We notice however that much of research on neural machine translation has focused on European languages despite its language agnostic nature. In this paper, we apply neural machine translation to the task of Arabic translation (Ar<->En) and compare it against a standard phrase-based translation system. We run extensive comparison using various configurations in preprocessing Arabic script and show that the phrase-based and neural translation systems perform comparably to each other and that proper preprocessing of Arabic script has a similar effect on both of the systems. We however observe that the neural machine translation significantly outperform the phrase-based system on an out-of-domain test set, making it attractive for real-world deployment.