33 citations · 33 across the 3 of their papers we have counts for
3 papers
Domain Specific Sub-network for Multi-Domain Neural Machine Translation
Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify +1
This paper presents Domain-Specific Sub-network (DoSS). It uses a set of masks obtained through pruning to define a sub-network for each domain and finetunes the sub-network parame…
Scalable and Efficient MoE Training for Multitask Multilingual Models
Young Jin Kim, Ammar Ahmad Awan, Alexandre Muzio +6
The Mixture of Experts (MoE) models are an emerging class of sparsely activated deep learning models that have sublinear compute costs with respect to their parameters. In contrast…
Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
Muhammad N. ElNokrashy, Amr Hendy, Mohamed Abdelghaffar +3
This paper describes our submission to the WMT20 sentence filtering task. We combine scores from (1) a custom LASER built for each source language, (2) a classifier built to distin…