Picture for Peyman Passban

Peyman Passban

Huawei Noah's Ark Lab

What is Lost in Knowledge Distillation?

Add code
Nov 07, 2023
Viaarxiv icon

Training Mixed-Domain Translation Models via Federated Learning

Add code
May 03, 2022
Figure 1 for Training Mixed-Domain Translation Models via Federated Learning
Figure 2 for Training Mixed-Domain Translation Models via Federated Learning
Figure 3 for Training Mixed-Domain Translation Models via Federated Learning
Figure 4 for Training Mixed-Domain Translation Models via Federated Learning
Viaarxiv icon

Dynamic Position Encoding for Transformers

Add code
Apr 18, 2022
Figure 1 for Dynamic Position Encoding for Transformers
Figure 2 for Dynamic Position Encoding for Transformers
Figure 3 for Dynamic Position Encoding for Transformers
Figure 4 for Dynamic Position Encoding for Transformers
Viaarxiv icon

Communication-Efficient Federated Learning for Neural Machine Translation

Add code
Dec 12, 2021
Figure 1 for Communication-Efficient Federated Learning for Neural Machine Translation
Figure 2 for Communication-Efficient Federated Learning for Neural Machine Translation
Viaarxiv icon

Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax

Add code
Jun 02, 2021
Figure 1 for Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
Figure 2 for Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
Figure 3 for Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
Figure 4 for Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
Viaarxiv icon

Robust Embeddings Via Distributions

Add code
Apr 17, 2021
Figure 1 for Robust Embeddings Via Distributions
Figure 2 for Robust Embeddings Via Distributions
Figure 3 for Robust Embeddings Via Distributions
Figure 4 for Robust Embeddings Via Distributions
Viaarxiv icon

Revisiting Robust Neural Machine Translation: A Transformer Case Study

Add code
Dec 31, 2020
Figure 1 for Revisiting Robust Neural Machine Translation: A Transformer Case Study
Figure 2 for Revisiting Robust Neural Machine Translation: A Transformer Case Study
Figure 3 for Revisiting Robust Neural Machine Translation: A Transformer Case Study
Figure 4 for Revisiting Robust Neural Machine Translation: A Transformer Case Study
Viaarxiv icon

ALP-KD: Attention-Based Layer Projection for Knowledge Distillation

Add code
Dec 27, 2020
Figure 1 for ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
Figure 2 for ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
Figure 3 for ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
Figure 4 for ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
Viaarxiv icon

Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers

Add code
Oct 06, 2020
Figure 1 for Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
Figure 2 for Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
Figure 3 for Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
Figure 4 for Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
Viaarxiv icon

Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation

Add code
Apr 17, 2018
Figure 1 for Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation
Figure 2 for Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation
Figure 3 for Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation
Figure 4 for Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation
Viaarxiv icon