no code implementations • WMT (EMNLP) 2020 • Muhammad N. ElNokrashy, Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Tawfik, Hany Hassan Awadalla
For the mBART finetuning setup, provided by the organizers, our method shows 7% and 5% relative improvement over baseline, in sacreBLEU score on the test set for Pashto and Khmer respectively.
no code implementations • WS 2019 • Ahmed Tawfik, Mahitab Emam, Khaled Essam, Robert Nabil, Hany Hassan
Parallel corpora available for building machine translation (MT) models for dialectal Arabic (DA) are rather limited.
no code implementations • IWSLT 2017 • Hany Hassan, Mostafa ElAraby, Ahmed Tawfik
Our approach is language independent and can be used to generate data for any variant of the source language such as slang or spoken dialect or even for a different language that is closely related to the source language.