Sentence Level Dialect Identification for Machine Translation System Selection

Wael Salloum, Heba Elfardy, Linda Alamir-Salloum, Nizar Habash, Mona T. Diab

Abstract: In this paper we study the use of sentencelevel dialect identification in optimizing machine translation system selection when translating mixed dialect input. We test our approach on Arabic, a prototypical diglossic language; and we optimize the combination of four different machine translation systems. Our best result improves over the best single MT system baseline by 1.0% BLEU and over a strong system selection baseline by 0.6% BLEU on a blind test set.