| Synthetic and natural noise both break neural machine translation Y Belinkov, Y Bisk arXiv preprint arXiv:1711.02173, 2017 | 485 | 2017 |
| Linguistic knowledge and transferability of contextual representations NF Liu, M Gardner, Y Belinkov, ME Peters, NA Smith arXiv preprint arXiv:1903.08855, 2019 | 443 | 2019 |
| Fine-grained analysis of sentence embeddings using auxiliary prediction tasks Y Adi, E Kermany, Y Belinkov, O Lavi, Y Goldberg arXiv preprint arXiv:1608.04207, 2016 | 417 | 2016 |
| Analysis methods in neural language processing: A survey Y Belinkov, J Glass Transactions of the Association for Computational Linguistics 7, 49-72, 2019 | 329 | 2019 |
| What do neural machine translation models learn about morphology? Y Belinkov, N Durrani, F Dalvi, H Sajjad, J Glass arXiv preprint arXiv:1704.03471, 2017 | 297 | 2017 |
| Analyzing the structure of attention in a transformer language model J Vig, Y Belinkov arXiv preprint arXiv:1906.04284, 2019 | 134 | 2019 |
| Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks Y Belinkov, L Màrquez, H Sajjad, N Durrani, F Dalvi, J Glass arXiv preprint arXiv:1801.07772, 2018 | 121* | 2018 |
| Identifying and Controlling Important Neurons in Neural Machine Translation A Bau, Y Belinkov, H Sajjad, N Durrani, F Dalvi, J Glass International Conference on Learning Representations, 2019 | 86 | 2019 |
| What is one grain of sand in the desert? analyzing individual neurons in deep nlp models F Dalvi, N Durrani, H Sajjad, Y Belinkov, A Bau, J Glass Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 6309-6317, 2019 | 78 | 2019 |
| Arabic Diacritization with Recurrent Neural Networks. Y Belinkov, JR Glass EMNLP, 2281-2285, 2015 | 65 | 2015 |
| Analyzing hidden representations in end-to-end automatic speech recognition systems Y Belinkov, J Glass Advances in Neural Information Processing Systems 30, 2017 | 61 | 2017 |
| End-to-end bias mitigation by modelling biases in corpora RK Mahabadi, Y Belinkov, J Henderson arXiv preprint arXiv:1909.06321, 2019 | 60 | 2019 |
| Translating dialectal arabic to english H Sajjad, K Darwish, Y Belinkov Proceedings of the 51st Annual Meeting of the Association for Computational …, 2013 | 60 | 2013 |
| Investigating gender bias in language models using causal mediation analysis J Vig, S Gehrmann, Y Belinkov, S Qian, D Nevo, Y Singer, S Shieber Advances in Neural Information Processing Systems 33, 12388-12401, 2020 | 58 | 2020 |
| VectorSLU: A continuous word vector approach to answer selection in community question answering systems Y Belinkov, M Mohtarami, S Cyphers, J Glass Proceedings of the 9th international workshop on semantic evaluation …, 2015 | 58 | 2015 |
| Understanding and improving morphological learning in the neural machine translation decoder F Dalvi, N Durrani, H Sajjad, Y Belinkov, S Vogel Proceedings of the Eighth International Joint Conference on Natural Language …, 2017 | 55 | 2017 |
| arTenTen: Arabic corpus and word sketches T Arts, Y Belinkov, N Habash, A Kilgarriff, V Suchomel Journal of King Saud University-Computer and Information Sciences 26 (4 …, 2014 | 55 | 2014 |
| A constructive prediction of the generalization error across scales JS Rosenfeld, A Rosenfeld, Y Belinkov, N Shavit arXiv preprint arXiv:1909.12673, 2019 | 54 | 2019 |
| Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference Y Belinkov, A Poliak, SM Shieber, B Van Durme, AM Rush arXiv preprint arXiv:1907.04380, 2019 | 51 | 2019 |
| Findings of the first shared task on machine translation robustness X Li, P Michel, A Anastasopoulos, Y Belinkov, N Durrani, O Firat, P Koehn, ... arXiv preprint arXiv:1906.11943, 2019 | 50 | 2019 |
James GlassMIT Computer Science and Artificial Intelligence LaboratoryVerified email at mit.edu
