| Enriching word vectors with subword information P Bojanowski, E Grave, A Joulin, T Mikolov Transactions of the Association for Computational Linguistics 5, 135-146, 2017 | 5207 | 2017 |
| Bag of tricks for efficient text classification A Joulin, E Grave, P Bojanowski, T Mikolov arXiv preprint arXiv:1607.01759, 2016 | 2614 | 2016 |
| Learning word vectors for 157 languages E Grave, P Bojanowski, P Gupta, A Joulin, T Mikolov arXiv preprint arXiv:1802.06893, 2018 | 645 | 2018 |
| Advances in pre-training distributed word representations T Mikolov, E Grave, P Bojanowski, C Puhrsch, A Joulin arXiv preprint arXiv:1712.09405, 2017 | 612 | 2017 |
| Fasttext. zip: Compressing text classification models A Joulin, E Grave, P Bojanowski, M Douze, H Jégou, T Mikolov arXiv preprint arXiv:1612.03651, 2016 | 479 | 2016 |
| Parseval networks: Improving robustness to adversarial examples M Cisse, P Bojanowski, E Grave, Y Dauphin, N Usunier arXiv preprint arXiv:1704.08847, 2017 | 432 | 2017 |
| Unsupervised cross-lingual representation learning at scale A Conneau, K Khandelwal, N Goyal, V Chaudhary, G Wenzek, F Guzmán, ... arXiv preprint arXiv:1911.02116, 2019 | 339 | 2019 |
| Colorless green recurrent networks dream hierarchically K Gulordava, P Bojanowski, E Grave, T Linzen, M Baroni arXiv preprint arXiv:1803.11138, 2018 | 239 | 2018 |
| Improving neural language models with a continuous cache E Grave, A Joulin, N Usunier arXiv preprint arXiv:1612.04426, 2016 | 198 | 2016 |
| Trace lasso: a trace norm regularization for correlated designs E Grave, GR Obozinski, F Bach Advances in Neural Information Processing Systems 24, 2187-2195, 2011 | 191 | 2011 |
| Efficient softmax approximation for gpus E Grave, A Joulin, M Cissé, D Grangier, H Jégou International Conference on Machine Learning, 1302-1310, 2017 | 177* | 2017 |
| Loss in translation: Learning bilingual word mapping with a retrieval criterion A Joulin, P Bojanowski, T Mikolov, H Jégou, E Grave arXiv preprint arXiv:1804.07745, 2018 | 130 | 2018 |
| Weakly-supervised alignment of video with text P Bojanowski, R Lajugie, E Grave, F Bach, I Laptev, J Ponce, C Schmid Proceedings of the IEEE international conference on computer vision, 4462-4470, 2015 | 105 | 2015 |
| Learning probabilistic phenotypes from heterogeneous EHR data R Pivovarov, AJ Perotte, E Grave, J Angiolillo, CH Wiggins, N Elhadad Journal of biomedical informatics 58, 156-165, 2015 | 97 | 2015 |
| Reducing transformer depth on demand with structured dropout A Fan, E Grave, A Joulin arXiv preprint arXiv:1909.11556, 2019 | 80 | 2019 |
| Unsupervised alignment of embeddings with wasserstein procrustes E Grave, A Joulin, Q Berthet The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 76 | 2019 |
| Adaptive attention span in transformers S Sukhbaatar, E Grave, P Bojanowski, A Joulin arXiv preprint arXiv:1905.07799, 2019 | 67 | 2019 |
| Can you tell me how to get past sesame street? sentence-level pretraining beyond language modeling A Wang, J Hula, P Xia, R Pappagari, RT McCoy, R Patel, N Kim, I Tenney, ... arXiv preprint arXiv:1812.10860, 2018 | 47* | 2018 |
| Longitudinal analysis of discussion topics in an online breast cancer community using convolutional neural networks S Zhang, E Grave, E Sklar, N Elhadad Journal of biomedical informatics 69, 1-9, 2017 | 47 | 2017 |
| End-to-end asr: from supervised to semi-supervised learning with modern architectures G Synnaeve, Q Xu, J Kahn, T Likhomanenko, E Grave, V Pratap, A Sriram, ... arXiv preprint arXiv:1911.08460, 2019 | 46 | 2019 |
Armand JoulinResearch Scientist, Facebook AI ResearchVerified email at fb.com
