Author Info
Name
Affiliation
Papers
MEHDI REZAGHOLIZADEH
Montreal Res Ctr, Huawei Noahs Ark Lab, Montreal, PQ, Canada
26
Collaborators
Citations 
PageRank 
46
3
8.82
Referers 
Referees 
References 
10
96
25
Title
Citations
PageRank
Year
Kronecker Decomposition for GPT Compression00.342022
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation.00.342022
From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables.00.342022
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation00.342022
CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation.00.342022
Learning functions on multiple sets using multi-set transformers.00.342022
Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition10.352021
NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation.00.342021
End-to-End Self-Debiasing Framework for Robust NLU Training.00.342021
Alp-Kd: Attention-Based Layer Projection For Knowledge Distillation00.342021
FINE-TUNING OF PRE-TRAINED END-TO-END SPEECH RECOGNITION WITH GENERATIVE ADVERSARIAL NETWORKS00.342021
Annealing Knowledge Distillation00.342021
How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding.00.342021
Towards Zero-Shot Knowledge Distillation for Natural Language Processing.00.342021
Universal-KD - Attention-based Output-Grounded Intermediate Layer Knowledge Distillation.00.342021
Knowledge Distillation with Noisy Labels for Natural Language Understanding.00.342021
Not Far Away, Not So Close - Sample Efficient Nearest Neighbour Data Augmentation via MiniMax.00.342021
Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation.00.342021
RW-KD - Sample-wise Loss Terms Re-Weighting for Knowledge Distillation.00.342021
Improving Word Embedding Factorization for Compression using Distilled Nonlinear Neural Decomposition.00.342020
Fully Quantized Transformer for Machine Translation.00.342020
Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation.00.342019
TextKD-GAN - Text Generation Using Knowledge Distillation and Generative Adversarial Networks.20.352019
Bilingual-GAN: A Step Towards Parallel Text Generation.00.342019
TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks.00.342019
SALSA-TEXT : self attentive latent space based adversarial text generation.00.342018