Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Amr Hendy

Amr Hendy
Alert button

Microsoft ATL Cairo

How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation


Feb 18, 2023
Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, Hany Hassan Awadalla

Add code
Alert button

Figure 1 for How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Figure 2 for How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Figure 3 for How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Figure 4 for How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Domain Specific Sub-network for Multi-Domain Neural Machine Translation


Oct 18, 2022
Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Y. Tawfik

Add code
Alert button

Figure 1 for Domain Specific Sub-network for Multi-Domain Neural Machine Translation
Figure 2 for Domain Specific Sub-network for Multi-Domain Neural Machine Translation
Figure 3 for Domain Specific Sub-network for Multi-Domain Neural Machine Translation
Figure 4 for Domain Specific Sub-network for Multi-Domain Neural Machine Translation
* 6 pages, 1 figure, 5 tables, AACL-IJCNLP 2022 conference 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation


Aug 11, 2022
Muhammad ElNokrashy, Amr Hendy, Mohamed Maher, Mohamed Afify, Hany Hassan Awadalla

Add code
Alert button

Figure 1 for Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
Figure 2 for Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
Figure 3 for Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
Figure 4 for Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
* 10 pages, accepted at AMTA-2022 (Association for Machine Translation in the Americas Conference) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs


Nov 26, 2021
Amr Hendy, Esraa A. Gad, Mohamed Abdelghaffar, Jailan S. ElMosalami, Mohamed Afify, Ahmed Y. Tawfik, Hany Hassan Awadalla

Add code
Alert button

Figure 1 for Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs
Figure 2 for Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs
Figure 3 for Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs
Figure 4 for Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Scalable and Efficient MoE Training for Multitask Multilingual Models


Sep 22, 2021
Young Jin Kim, Ammar Ahmad Awan, Alexandre Muzio, Andres Felipe Cruz Salinas, Liyang Lu, Amr Hendy, Samyam Rajbhandari, Yuxiong He, Hany Hassan Awadalla

Add code
Alert button

Figure 1 for Scalable and Efficient MoE Training for Multitask Multilingual Models
Figure 2 for Scalable and Efficient MoE Training for Multitask Multilingual Models
Figure 3 for Scalable and Efficient MoE Training for Multitask Multilingual Models
Figure 4 for Scalable and Efficient MoE Training for Multitask Multilingual Models

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions


Nov 16, 2020
Muhammad N. ElNokrashy, Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Tawfik, Hany Hassan Awadalla

Add code
Alert button

Figure 1 for Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
Figure 2 for Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
Figure 3 for Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
Figure 4 for Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions
* Accepted at WMT20 (EMNLP 2020 Fifth Conference on Machine Translation) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email