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 David Grangier

The Trade-offs of Domain Adaptation for Neural Language Models


Sep 21, 2021
Dan Iter, David Grangier


  Access Paper or Ask Questions

On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation


Sep 15, 2021
Dan Iter, David Grangier


  Access Paper or Ask Questions

Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral


Aug 25, 2021
Lucio M. Dery, Yann Dauphin, David Grangier

* 15 pages, 3 figures, Accepted to International Conference on Learning Representations (ICLR) 2021 See https://github.com/ldery/ATTITTUD}{https://github.com/ldery/ATTITTUD for associated code 

  Access Paper or Ask Questions

What Can Unsupervised Machine Translation Contribute to High-Resource Language Pairs?


Jun 30, 2021
Kelly Marchisio, Markus Freitag, David Grangier


  Access Paper or Ask Questions

DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding


May 28, 2021
Neil Zeghidour, Olivier Teboul, David Grangier


  Access Paper or Ask Questions

Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation


Apr 29, 2021
Markus Freitag, George Foster, David Grangier, Viresh Ratnakar, Qijun Tan, Wolfgang Macherey


  Access Paper or Ask Questions

Learning from Heterogeneous EEG Signals with Differentiable Channel Reordering


Oct 21, 2020
Aaqib Saeed, David Grangier, Olivier Pietquin, Neil Zeghidour


  Access Paper or Ask Questions

Contrastive Learning of General-Purpose Audio Representations


Oct 21, 2020
Aaqib Saeed, David Grangier, Neil Zeghidour


  Access Paper or Ask Questions

Human-Paraphrased References Improve Neural Machine Translation


Oct 20, 2020
Markus Freitag, George Foster, David Grangier, Colin Cherry

* Accepted at WMT 2020 

  Access Paper or Ask Questions

Toward Better Storylines with Sentence-Level Language Models


May 11, 2020
Daphne Ippolito, David Grangier, Douglas Eck, Chris Callison-Burch

* ACL 2020 short paper 

  Access Paper or Ask Questions

BLEU might be Guilty but References are not Innocent


Apr 13, 2020
Markus Freitag, David Grangier, Isaac Caswell


  Access Paper or Ask Questions

Efficient Content-Based Sparse Attention with Routing Transformers


Mar 12, 2020
Aurko Roy, Mohammad Saffar, Ashish Vaswani, David Grangier


  Access Paper or Ask Questions

Wavesplit: End-to-End Speech Separation by Speaker Clustering


Feb 20, 2020
Neil Zeghidour, David Grangier


  Access Paper or Ask Questions

Translationese as a Language in "Multilingual" NMT


Nov 10, 2019
Parker Riley, Isaac Caswell, Markus Freitag, David Grangier


  Access Paper or Ask Questions

ELI5: Long Form Question Answering


Jul 22, 2019
Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, Michael Auli


  Access Paper or Ask Questions

Tagged Back-Translation


Jun 15, 2019
Isaac Caswell, Ciprian Chelba, David Grangier

* Accepted as oral presentation in WMT 2019; 9 pages; 9 tables; 1 figure 

  Access Paper or Ask Questions

Unsupervised Paraphrasing without Translation


May 29, 2019
Aurko Roy, David Grangier

* ACL 2019 

  Access Paper or Ask Questions

fairseq: A Fast, Extensible Toolkit for Sequence Modeling


Apr 01, 2019
Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli

* NAACL 2019 Demo paper 

  Access Paper or Ask Questions

Modeling Human Motion with Quaternion-based Neural Networks


Jan 21, 2019
Dario Pavllo, Christoph Feichtenhofer, Michael Auli, David Grangier

* arXiv admin note: substantial text overlap with arXiv:1805.06485 

  Access Paper or Ask Questions

3D human pose estimation in video with temporal convolutions and semi-supervised training


Nov 28, 2018
Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli

* 13 pages 

  Access Paper or Ask Questions

Classical Structured Prediction Losses for Sequence to Sequence Learning


Oct 05, 2018
Sergey Edunov, Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato

* 10 pages, NAACL 2018 

  Access Paper or Ask Questions

Understanding Back-Translation at Scale


Oct 03, 2018
Sergey Edunov, Myle Ott, Michael Auli, David Grangier

* 12 pages; EMNLP 2018 

  Access Paper or Ask Questions

Scaling Neural Machine Translation


Sep 04, 2018
Myle Ott, Sergey Edunov, David Grangier, Michael Auli

* WMT 2018 

  Access Paper or Ask Questions

Analyzing Uncertainty in Neural Machine Translation


Aug 13, 2018
Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato

* ICML 2018 

  Access Paper or Ask Questions

QuaterNet: A Quaternion-based Recurrent Model for Human Motion


Jul 31, 2018
Dario Pavllo, David Grangier, Michael Auli

* British Machine Vision Conference (BMVC), 2018 

  Access Paper or Ask Questions

Controllable Abstractive Summarization


May 18, 2018
Angela Fan, David Grangier, Michael Auli

* ACL2018 Workshop on Neural Machine Translation and Generation ([email protected]

  Access Paper or Ask Questions

Iterative Refinement for Machine Translation


Apr 13, 2018
Roman Novak, Michael Auli, David Grangier

* Presented as a poster at BayLearn 2017 

  Access Paper or Ask Questions

QuickEdit: Editing Text & Translations by Crossing Words Out


Mar 28, 2018
David Grangier, Michael Auli

* NAACL'18 

  Access Paper or Ask Questions

Language Modeling with Gated Convolutional Networks


Sep 08, 2017
Yann N. Dauphin, Angela Fan, Michael Auli, David Grangier


  Access Paper or Ask Questions

Convolutional Sequence to Sequence Learning


Jul 25, 2017
Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin


  Access Paper or Ask Questions