Domain and Dialect Adaptation for Machine Translation into Egyptian Arabic

In this paper, we present a statistical machine translation system for English to Dialectal Arabic (DA), using Modern Standard Arabic (MSA) as a pivot. We create a core system to translate from English to MSA using a large bilingual parallel corpus. Then, we design two separate pathways for translation from MSA into DA: a two-step domain and dialect adaptation system and a one-step simultaneous domain and dialect adaptation system. Both variants of the adaptation systems are trained on a 100k sentence tri-parallel corpus of English, MSA, and Egyptian Arabic generated by a rule-based transformation. We test our systems on a held-out Egyptian Arabic test set from the 100k sentence corpus and we achieve our best performance using the two-step domain and dialect adaptation system with a BLEU score of 42.9.