Alexis Conneau

is this you? claim profile

∙ 0 followers
Facebook

Alexis Conneau is a resident Ph.D. student at Facebook AI Research in Paris. Set to receive his Ph.D. in Artificial Intelligence from Le Mans University in 2019, Conneau’s current focus is in the area of deep learning for natural language processing (NLP). Specifically, he is working on transferable text representations using neural networks.

Conneau received a B.S. and a Master of Applied Mathematics degree from Ecole Polytechnique before getting a master’s degree in vision and machine learning with the math, vision, and learning (MVA) between ENS Cachan and ENSAE.

He spent six months as a research intern in the area of machine learning at the hedge fund management company, Capital Fund Management, in 2014. In 2015, he spent another six months as a research intern in the same area at Criteo, the personalized retargeting company.

Conneau knows Python, and his research interests include natural language understanding, sequence to sequence learning, and neural machine translation.

Featured Co-authors

Yann LeCun
81 publications
Luke Zettlemoyer
77 publications
Armand Joulin
51 publications
Samuel R. Bowman
50 publications
Michael Auli
49 publications
Douwe Kiela
48 publications
Gabriel Synnaeve
44 publications
Hervé Jégou
41 publications
Marc'Aurelio Ranzato
41 publications
Ronan Collobert
40 publications
Edouard Grave
39 publications

Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning

State-of-the-art natural language understanding classification models fo...
11/03/2020 ∙ by Beliz Gunel, et al. ∙ 16 ∙ share

read it
Self-training and Pre-training are Complementary for Speech Recognition

Self-training and unsupervised pre-training have emerged as effective ap...
10/22/2020 ∙ by Qiantong Xu, et al. ∙ 0 ∙ share

read it
Self-training Improves Pre-training for Natural Language Understanding

Unsupervised pre-training has led to much recent progress in natural lan...
10/05/2020 ∙ by Jingfei Du, et al. ∙ 0 ∙ share

read it
Unsupervised Cross-lingual Representation Learning for Speech Recognition

This paper presents XLSR which learns cross-lingual speech representatio...
06/24/2020 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Unsupervised Cross-lingual Representation Learning at Scale

This paper shows that pretraining multilingual language models at scale ...
11/05/2019 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Emerging Cross-lingual Structure in Pretrained Language Models

We study the problem of multilingual masked language modeling, i.e. the ...
11/04/2019 ∙ by Shijie Wu, et al. ∙ 0 ∙ share

read it
CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data

Pre-training text representations have led to significant improvements i...
11/01/2019 ∙ by Guillaume Wenzek, et al. ∙ 13 ∙ share

read it
Cross-lingual Language Model Pretraining

Recent studies have demonstrated the efficiency of generative pretrainin...
01/22/2019 ∙ by Guillaume Lample, et al. ∙ 0 ∙ share

read it
XNLI: Evaluating Cross-lingual Sentence Representations

State-of-the-art natural language processing systems rely on supervision...
09/13/2018 ∙ by Alexis Conneau, et al. ∙ 8 ∙ share

read it
What you can cram into a single vector: Probing sentence embeddings for linguistic properties

Although much effort has recently been devoted to training high-quality ...
05/03/2018 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Phrase-Based & Neural Unsupervised Machine Translation

Machine translation systems achieve near human-level performance on some...
04/20/2018 ∙ by Guillaume Lample, et al. ∙ 0 ∙ share

read it
SentEval: An Evaluation Toolkit for Universal Sentence Representations

We introduce SentEval, a toolkit for evaluating the quality of universal...
03/14/2018 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Word Translation Without Parallel Data

State-of-the-art methods for learning cross-lingual word embeddings have...
10/11/2017 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Learning Visually Grounded Sentence Representations

We introduce a variety of models, trained on a supervised image captioni...
07/19/2017 ∙ by Douwe Kiela, et al. ∙ 0 ∙ share

read it
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Many modern NLP systems rely on word embeddings, previously trained in a...
05/05/2017 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it
Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation

We propose Meta-Prod2vec, a novel method to compute item similarities fo...
07/25/2016 ∙ by Flavian Vasile, et al. ∙ 0 ∙ share

read it
Very Deep Convolutional Networks for Text Classification

The dominant approach for many NLP tasks are recurrent neural networks, ...
06/06/2016 ∙ by Alexis Conneau, et al. ∙ 0 ∙ share

read it