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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning


Jun 02, 2022
Yuchen Lu, Zhen Liu, Aristide Baratin, Romain Laroche, Aaron Courville, Alessandro Sordoni


   Access Paper or Ask Questions

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

Evaluating Distributional Distortion in Neural Language Modeling


Mar 24, 2022
Benjamin LeBrun, Alessandro Sordoni, Timothy J. O'Donnell

* International Conference on Learning Representations. 2022 

   Access Paper or Ask Questions

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

Better Language Model with Hypernym Class Prediction


Mar 21, 2022
He Bai, Tong Wang, Alessandro Sordoni, Peng Shi

* ACL 2022 

   Access Paper or Ask Questions

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

Combining Modular Skills in Multitask Learning


Mar 01, 2022
Edoardo M. Ponti, Alessandro Sordoni, Yoshua Bengio, Siva Reddy


   Access Paper or Ask Questions

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

Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge


Dec 16, 2021
Ian Porada, Alessandro Sordoni, Jackie Chi Kit Cheung


   Access Paper or Ask Questions

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

Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU


Sep 17, 2021
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata Mukherjee

* To Appear in EMNLP 2021 

   Access Paper or Ask Questions

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

The Emergence of the Shape Bias Results from Communicative Efficiency


Sep 15, 2021
Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche

* Accepted at CoNLL 2021 

   Access Paper or Ask Questions

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

Decomposed Mutual Information Estimation for Contrastive Representation Learning


Jun 25, 2021
Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Phil Bachman, Remi Tachet

* ICML 2021 

   Access Paper or Ask Questions

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

Understanding by Understanding Not: Modeling Negation in Language Models


May 07, 2021
Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, R Devon Hjelm, Alessandro Sordoni, Aaron Courville


   Access Paper or Ask Questions

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

Linguistic dependencies and statistical dependence


Apr 18, 2021
Jacob Louis Hoover, Alessandro Sordoni, Wenyu Du, Timothy J. O'Donnell

* 8 pages, plus references and appendices 

   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
>>