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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement


Nov 12, 2022
Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk

Add code

* ENLSP-II NeurIPS Workshop 2022, 6 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages


Oct 18, 2022
Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation


Oct 14, 2022
Mojtaba Valipour, Mehdi Rezagholizadeh, Ivan Kobyzev, Ali Ghodsi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Integer Fine-tuning of Transformer-based Models


Sep 20, 2022
Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Functions on Multiple Sets using Multi-Set Transformers


Jun 30, 2022
Kira Selby, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models


May 25, 2022
Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh, Tianda Li, Alan Do-Omri, Peng Lu, Ali Ghodsi, Pascal Poupart

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding


May 21, 2022
Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Duan Xinyu, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Philippe Langlais

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Dynamic Position Encoding for Transformers


Apr 18, 2022
Joyce Zheng, Mehdi Rezagholizadeh, Peyman Passban

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation


Apr 15, 2022
Md Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation


Mar 17, 2022
Ehsan Kamalloo, Mehdi Rezagholizadeh, Ali Ghodsi

Add code

* ACL 2022 Findings 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
>>