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 Paul Michel

Balancing Average and Worst-case Accuracy in Multitask Learning

Oct 12, 2021
Paul Michel, Sebastian Ruder, Dani Yogatama

* Under review 

  Access Paper or Ask Questions

Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative

Sep 15, 2021
Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig

* 16 pages, 4 figures 

  Access Paper or Ask Questions

Learning Neural Models for Natural Language Processing in the Face of Distributional Shift

Sep 03, 2021
Paul Michel

* PhD thesis 

  Access Paper or Ask Questions

Examining and Combating Spurious Features under Distribution Shift

Jun 14, 2021
Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig

* Accepted by ICML2021 

  Access Paper or Ask Questions

Modeling the Second Player in Distributionally Robust Optimization

Mar 31, 2021
Paul Michel, Tatsunori Hashimoto, Graham Neubig

* Accepted at ICLR 2021 

  Access Paper or Ask Questions

Weight Poisoning Attacks on Pre-trained Models

Apr 14, 2020
Keita Kurita, Paul Michel, Graham Neubig

* Published as a long paper at ACL 2020 

  Access Paper or Ask Questions

Optimizing Data Usage via Differentiable Rewards

Nov 22, 2019
Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Graham Neubig, Jaime Carbonell

  Access Paper or Ask Questions

Findings of the First Shared Task on Machine Translation Robustness

Jul 03, 2019
Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Pino, Hassan Sajjad

  Access Paper or Ask Questions

Are Sixteen Heads Really Better than One?

May 25, 2019
Paul Michel, Omer Levy, Graham Neubig

  Access Paper or Ask Questions

compare-mt: A Tool for Holistic Comparison of Language Generation Systems

Mar 19, 2019
Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang

* NAACL 2019 Demo Paper 

  Access Paper or Ask Questions

On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models

Mar 19, 2019
Paul Michel, Xian Li, Graham Neubig, Juan Miguel Pino

* NAACL-HLT 2019 long paper 

  Access Paper or Ask Questions

MTNT: A Testbed for Machine Translation of Noisy Text

Sep 02, 2018
Paul Michel, Graham Neubig

* EMNLP 2018 Long Paper 

  Access Paper or Ask Questions

Extreme Adaptation for Personalized Neural Machine Translation

May 04, 2018
Paul Michel, Graham Neubig

* Accepted as a short paper at ACL 2018 

  Access Paper or Ask Questions

Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology Based Representations

May 31, 2017
Paul Michel, Abhilasha Ravichander, Shruti Rijhwani

* 5 pages, 3 figures. Rep4NLP workshop at ACL 2017 

  Access Paper or Ask Questions

Blind phoneme segmentation with temporal prediction errors

May 27, 2017
Paul Michel, Okko Räsänen, Roland Thiollière, Emmanuel Dupoux

* 7 pages 3 figures. Presented at ACL SRW 2017 

  Access Paper or Ask Questions

DyNet: The Dynamic Neural Network Toolkit

Jan 15, 2017
Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin

* 33 pages 

  Access Paper or Ask Questions