| Lingvo: a modular and scalable framework for sequence-to-sequence modeling J Shen, P Nguyen, Y Wu, Z Chen, MX Chen, Y Jia, A Kannan, T Sainath, ... arXiv preprint arXiv:1902.08295, 2019 | 199 | 2019 |
| High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics M Freitag, D Grangier, Q Tan, B Liang Transactions of the Association for Computational Linguistics 10, 811-825, 2022 | 39 | 2022 |
| Minimum Bayes Risk Decoding with Neural Metrics of Translation Quality M Freitag, D Grangier, Q Tan, B Liang arXiv preprint arXiv:2111.09388, 2021 | 11 | 2021 |
| Contrastive Sequence-to-Sequence Data Selector W Wang, B Liang, M Hughes, T Watanabe, T Nakagawa, A Rudnick US Patent US Patent App. 16/376,254, 2019 | 2 | 2019 |
| The Implicit Length Bias of Label Smoothing on Beam Search Decoding B Liang, P Wang, Y Cao arXiv preprint arXiv:2205.00659, 2022 | | 2022 |
| Self-Supervised Learning for Pairwise Data Refinement GH Abrego, B Liang, W Wang, Z Parekh, Y Yang, Y Sung Proceedings of the 1st Conference of the Asia-Pacific Chapter of the …, 2020 | | 2020 |
