@inproceedings{2aa97205f24d49d6b16d29c67b119c4a,
title = "Domain and Dialect Adaptation for Machine Translation into Egyptian Arabic",
abstract = "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.",
author = "Serena Jeblee and Weston Feely and Houda Bouamor and Alon Lavie and Nizar Habash and Kemal Oflazer",
note = "Publisher Copyright: {\textcopyright}2014 Association for Computational Linguistics; EMNLP 2014 Workshop on Arabic Natural Language Processing, ANLP 2014 ; Conference date: 25-10-2014",
year = "2014",
language = "English (US)",
series = "ANLP 2014 - EMNLP 2014 Workshop on Arabic Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "196--206",
editor = "Nizar Habash and Stephan Vogel",
booktitle = "ANLP 2014 - EMNLP 2014 Workshop on Arabic Natural Language Processing, Proceedings",
}