Edouard Grave

Edouard is a Research Scientist at Facebook AI Research (FAIR) in Paris, working on machine learning and natural language processing. Before joining Facebook, he was a postdoctoral research scientist at Columbia University and UC Berkeley. He obtained his Ph.D. in computer science from Université Paris VI and graduated from École Polytechnique with an MSc in machine learning and computer vision.

Edouard's Publications

May 03, 2020

RESEARCH

Adaptive Attention Span in Transformers

We propose a novel self-attention mechanism that can learn its optimal attention span. This allows us to extend significantly the maximum context size used in Transformer, while maintaining control over their memory footprint and computational…

Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, Armand Joulin,

May 03, 2020

May 03, 2020

RESEARCH

NLP

Unsupervised Hyper-alignment for Multilingual Word Embeddings

We consider the problem of aligning continuous word representations, learned in multiple languages, to a common space. It was recently shown that, in the case of two languages, it is possible to learn such a mapping without supervision. This…

Jean Alaux, Edouard Grave, Marco Cuturi, Armand Joulin,

May 03, 2020

May 03, 2020

RESEARCH

NLP

Learning Word Vectors for 157 Languages

Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredient to the successful application of these representations is to…

Edouard Grave, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, Tomas Mikolov,

May 03, 2020