| No language left behind: Scaling human-centered machine translation MR Costa-jussà, J Cross, O Çelebi, M Elbayad, K Heafield, K Heffernan, ... arXiv preprint arXiv:2207.04672, 2022 | 551 | 2022 |
| Deep encoder, shallow decoder: Reevaluating non-autoregressive machine translation J Kasai, N Pappas, H Peng, J Cross, NA Smith arXiv preprint arXiv:2006.10369, 2020 | 163 | 2020 |
| Monotonic multihead attention X Ma, J Pino, J Cross, L Puzon, J Gu arXiv preprint arXiv:1909.12406, 2019 | 138 | 2019 |
| Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles J Cross, L Huang EMNLP, 2016 | 133 | 2016 |
| Incremental Parsing with Minimal Features Using Bi-Directional LSTM J Cross, L Huang ACL, 2016 | 98 | 2016 |
| Lifting the curse of multilinguality by pre-training modular transformers J Pfeiffer, N Goyal, XV Lin, X Li, J Cross, S Riedel, M Artetxe arXiv preprint arXiv:2205.06266, 2022 | 94 | 2022 |
| Facebook ai wmt21 news translation task submission C Tran, S Bhosale, J Cross, P Koehn, S Edunov, A Fan arXiv preprint arXiv:2108.03265, 2021 | 89 | 2021 |
| Non-autoregressive machine translation with disentangled context transformer J Kasai, J Cross, M Ghazvininejad, J Gu International conference on machine learning, 5144-5155, 2020 | 88 | 2020 |
| Simple Fusion: Return of the Language Model F Stahlberg, J Cross, V Stoyanov WMT, 2018 | 76 | 2018 |
| Improving zero-shot translation by disentangling positional information D Liu, J Niehues, J Cross, F Guzmán, X Li arXiv preprint arXiv:2012.15127, 2020 | 39 | 2020 |
| Parallel machine translation with disentangled context transformer J Kasai, J Cross, M Ghazvininejad, J Gu arXiv preprint arXiv:2001.05136, 2020 | 30 | 2020 |
| On the evaluation of machine translation for terminology consistency A Anastasopoulos, L Besacier, J Cross, M Gallé, P Koehn, V Nikoulina arXiv preprint arXiv:2106.11891, 2021 | 29 | 2021 |
| Multilingual neural machine translation with deep encoder and multiple shallow decoders X Kong, A Renduchintala, J Cross, Y Tang, J Gu, X Li Proceedings of the 16th Conference of the European Chapter of the …, 2021 | 27 | 2021 |
| Tricks for training sparse translation models D Dua, S Bhosale, V Goswami, J Cross, M Lewis, A Fan arXiv preprint arXiv:2110.08246, 2021 | 22 | 2021 |
| Multilingual machine translation with hyper-adapters C Baziotis, M Artetxe, J Cross, S Bhosale arXiv preprint arXiv:2205.10835, 2022 | 21 | 2022 |
| Generating distributed word embeddings using structured information JH Cross, JJ Fan, B Xiang, B Zhou US Patent 9,892,113, 2018 | 16 | 2018 |
| Data selection curriculum for neural machine translation T Mohiuddin, P Koehn, V Chaudhary, J Cross, S Bhosale, S Joty arXiv preprint arXiv:2203.13867, 2022 | 14 | 2022 |
| Generating distributed word embeddings using structured information JH Cross, JJ Fan, B Xiang, B Zhou US Patent 9,898,458, 2018 | 13 | 2018 |
| How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training? S Zhang, V Chaudhary, N Goyal, J Cross, G Wenzek, M Bansal, ... arXiv preprint arXiv:2204.14268, 2022 | 12 | 2022 |
| Alternative input signals ease transfer in multilingual machine translation S Sun, A Fan, J Cross, V Chaudhary, C Tran, P Koehn, F Guzmán arXiv preprint arXiv:2110.07804, 2021 | 12 | 2021 |
