| Bert loses patience: Fast and robust inference with early exit W Zhou, C Xu, T Ge, J McAuley, K Xu, F Wei Advances in Neural Information Processing Systems 33, 18330-18341, 2020 | 299 | 2020 |
| Bert-of-theseus: Compressing bert by progressive module replacing C Xu, W Zhou, T Ge, F Wei, M Zhou arXiv preprint arXiv:2002.02925, 2020 | 211 | 2020 |
| Max-margin tensor neural network for Chinese word segmentation W Pei, T Ge, B Chang Proceedings of the 52nd Annual Meeting of the Association for Computational …, 2014 | 204 | 2014 |
| Towards time-aware knowledge graph completion T Jiang, T Liu, T Ge, L Sha, B Chang, S Li, Z Sui Proceedings of COLING 2016, the 26th International Conference on …, 2016 | 173 | 2016 |
| Fluency boost learning and inference for neural grammatical error correction T Ge, F Wei, M Zhou Proceedings of the 56th Annual Meeting of the Association for Computational …, 2018 | 140 | 2018 |
| Encoding temporal information for time-aware link prediction T Jiang, T Liu, T Ge, L Sha, S Li, B Chang, Z Sui Proceedings of the 2016 conference on empirical methods in natural language …, 2016 | 132 | 2016 |
| Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration Z Wang, S Mao, W Wu, T Ge, F Wei, H Ji arXiv preprint arXiv:2307.05300, 2023 | 122 | 2023 |
| BERT-based lexical substitution W Zhou, T Ge, K Xu, F Wei, M Zhou Proceedings of the 57th annual meeting of the association for computational …, 2019 | 121 | 2019 |
| Parallel data augmentation for formality style transfer Y Zhang, T Ge, X Sun arXiv preprint arXiv:2005.07522, 2020 | 103* | 2020 |
| Reaching human-level performance in automatic grammatical error correction: An empirical study T Ge, F Wei, M Zhou arXiv preprint arXiv:1807.01270, 2018 | 87 | 2018 |
| Exploiting task-oriented resources to learn word embeddings for clinical abbreviation expansion Y Liu, T Ge, KS Mathews, H Ji, DL McGuinness arXiv preprint arXiv:1804.04225, 2018 | 83 | 2018 |
| An effective neural network model for graph-based dependency parsing W Pei, T Ge, B Chang Proceedings of the 53rd Annual Meeting of the Association for Computational …, 2015 | 79 | 2015 |
| In-context autoencoder for context compression in a large language model T Ge, J Hu, L Wang, X Wang, SQ Chen, F Wei arXiv preprint arXiv:2307.06945, 2023 | 63 | 2023 |
| Instantaneous grammatical error correction with shallow aggressive decoding X Sun, T Ge, F Wei, H Wang arXiv preprint arXiv:2106.04970, 2021 | 49 | 2021 |
| Improving the efficiency of grammatical error correction with erroneous span detection and correction M Chen, T Ge, X Zhang, F Wei, M Zhou arXiv preprint arXiv:2010.03260, 2020 | 49 | 2020 |
| Beyond preserved accuracy: Evaluating loyalty and robustness of BERT compression C Xu, W Zhou, T Ge, K Xu, J McAuley, F Wei arXiv preprint arXiv:2109.03228, 2021 | 44 | 2021 |
| Inference with reference: Lossless acceleration of large language models N Yang, T Ge, L Wang, B Jiao, D Jiang, L Yang, R Majumder, F Wei arXiv preprint arXiv:2304.04487, 2023 | 43 | 2023 |
| Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation H Xia, T Ge, P Wang, SQ Chen, F Wei, Z Sui Findings of the Association for Computational Linguistics: EMNLP 2023, 3909-3925, 2023 | 41* | 2023 |
| Low-code llm: Visual programming over llms Y Cai, S Mao, W Wu, Z Wang, Y Liang, T Ge, C Wu, W You, T Song, Y Xia, ... arXiv preprint arXiv:2304.08103 2, 2023 | 41 | 2023 |
| Formality style transfer with hybrid textual annotations R Xu, T Ge, F Wei arXiv preprint arXiv:1903.06353, 2019 | 40 | 2019 |
Furu WeiPartner Research Manager, Microsoft ResearchVerified email at microsoft.com