邮箱:xiaotong@mail.neu.edu.cn
个人主页:Tong Xiao's homepage
个人简介
肖桐,博士,东北大学教授、博士生导师,东北大学计算机学院人工智能系主任,东北大学自然语言处理实验室主任,小牛翻译(NiuTrans)联合创始人。于东北大学计算机专业获得博士学位。2006—2009年赴日本富士施乐、微软亚洲研究院访问学习,并于2013—2014年赴英国剑桥大学开展博士后研究。主要研究领域包括自然语言处理、机器翻译、语言模型等。在国内外相关领域高水平会议及期刊上发表学术论文100余篇,并撰写专著《机器翻译:基础与模型》。作为项目技术负责人,成功研发了NiuTrans、NiuTensor等开源系统(https://github.com/NiuTrans),在WMT、CCMT/CWMT、NTCIR等国内外评测中30余次获得冠军。2016年获得中国中文信息学会“钱伟长中文信息处理科学技术奖”一等奖,2021年获得中国计算机学会CCF-NLP青年新锐奖。任ACL、EMNLP、AAAI等国际著名会议及期刊的领域主席、高级程序委员会委员,并多次获得ACL、NAACL等会议的Outstanding Reviewer、Outstanding Action Editor。
代表性论著
《机器翻译:基础与模型》, 肖桐 朱靖波, 电子工业出版社,2021. 开源版本地址:https://github.com/NiuTrans/MTBook
机器翻译建模:
Learning Deep Transformer Models for Machine Translation, Qiang Wang, Bei Li, Tong Xiao, Jingbo Zhu, Changliang Li, Derek F. Wong, Lidia S. Chao.In Proc. of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019, Florence, Italy.
Learning Multiscale Transformer Models for Sequence Generation. Bei Li, Tong Zheng, Yi Jing, Chengbo Jiao, Tong Xiao, Jingbo Zhu. In Proc. of the 39th International Conference on Machine Learning(PMLR), 2022, Baltimore, Maryland, USA
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation. Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, JingBo Zhu, Xuebo Liu, and Min Zhang. In Proc. of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), 2022, Dublin, Ireland.
Bagging and Boosting Statistical Machine Translation Systems, Tong Xiao, Jingbo Zhu and Tongran Liu. Artificial Intelligence (AI) , 2013, 195: 496-527.
端到端语音翻译:
Recent Advances in Direct Speech-to-text Translation. Chen Xu, Rong Ye, Qianqian Dong, Chengqi Zhao, Tom Ko, Mingxuan Wang, Tong Xiao, Jingbo Zhu. In Proc. of the Thirty-Second International Joint Conference on Artificial Intelligence(IJCAI), 2023, Macao, SAR
Improving end-to-end speech translation by leveraging auxiliary speech and text data. Yuhao Zhang, Chen Xu, Bojie Hu, Chunliang Zhang, Tong Xiao, Jingbo Zhu. In Proc. of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence, 2023, Washington DC, USA.
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders , Chen Xu, Bojie Hu, Yanyang Li, Yuhao Zhang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu.In Proc. of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), 2021, Virtual Event.
语言模型:
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection. Chenglong Wang, Yi Lu, Yongyu Mu, Yimin Hu, Tong Xiao, and Jingbo Zhu. In Findings of the Association for Computational Linguistics: EMNLP, 2022, Abu Dhabi, United Arab Emirates.
Learning Architectures from an Extended Search Space for Language Modeling, Yinqiao Li, Chi Hu, Yuhao Zhang, Nuo Xu, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li. In Proc. of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), 2020, Seattle, USA.
Language Modeling for Syntax-based Machine Translation Using Tree Substitution Grammars: A Case Study on Chinese-English Translation, Tong Xiao, Jingbo Zhu and Muhua Zhu. In ACM Transactions on Asian Language Information Processing (TALIP), 2011, Speical Issue on Chinese Language Processing
高效方法
MobileNMT: Enabling Translation in 15MB and 30ms. Ye Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, and Jingbo Zhu. In Proc. of the 61st Annual Meeting of the Association for Computational Linguistics (ACL: Industry Track), 2023, Toronto, Canada.
Weight Distillation: Transferring the Knowledge in Neural Network Parameters , Ye Lin, Yanyang Li, Ziyang Wang, Bei Li, Quan Du, Tong Xiao and Jingbo Zhu. In Proc. of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), 2021, Virtual Event.
Learning Light-Weight Translation Models from Deep Transformer , Bei Li, ZiyangWang, Hui Liu, Quan Du, Tong Xiao, Chunliang Zhang, Jingbo Zhu. In Proc. of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021, Virtual Event.
Sharing Attention Weights for Fast Transformer, Tong Xiao, Yinqiao Li, Jingbo Zhu, Zhengtao Yu and Tongran Liu. In Proc. of the 28th International Joint Conference on Artificial Intelligence (IJCAI) , 2020, Macao, China.
技术评测
IWSLT2023 Offline speech translation English-Chinese (Constrainted, End-to-End) - 1st place
The NiuTrans End-to-End Speech Translation System for IWSLT23 English-to-Chinese Offline Task. Yuchen Han, Xiaoqian Liu , Hao Chen, Yuhao Zhang, Chen Xu, Tong Xiao, and Jingbo Zhu. In Proc. of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 211–218, Toronto, Canada (in-person and online).
WMT22 Chinese-English, English-Chinese- 1st place, 2nd place (Human Evaluation)
The NiuTrans Machine Translation Systems for WMT22. Weiqiao Shan, Zhiquan Cao, Yuchen Han, Siming Wu, Yimin Hu, Jie Wang, Yi Zhang, Hou Baoyu, Hang Cao, Chenghao Gao, Xiaowen Liu, Tong Xiao, Anxiang Ma, and Jingbo Zhu. 2022. In Proc. of the Seventh Conference on Machine Translation (WMT 2022), pages 366–374, Abu Dhabi, United Arab Emirates (Hybrid).
IWSLT 2022 Offline Speech Translation English-Chinese (End-to-End) - 3rd place
The NiuTrans's Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task. Yuhao Zhang, Canan Huang, Chen Xu, Xiaoqian Liu, Bei Li, Anxiang Ma, Tong Xiao, Jingbo Zhu. In Proc. of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 232–238, Dublin, Ireland (in-person and online).
WMT21 Chinese-English, Englist-Hausa, Japanese-English, Icelandic-English, English-Icelandic, Russian-English, English-Japanese - 1st place, 2nd place, 2nd place, 3rd place, 3rd place, 3rd place, 3rd place (Human Evaluation)
The NiuTrans Machine Translation Systems for WMT21. Shuhan Zhou, Tao Zhou, Binghao Wei, Yingfeng Luo, Yongyu Mu, Zefan Zhou, Chenglong Wang, Xuanjun Zhou, Chuanhao Lv, Yi Jing, Laohu Wang, Jingnan Zhang, Canan Huang, Zhongxiang Yan, Chi Hu, Bei Li, Tong Xiao, and Jingbo Zhu. 2021. In Proc. of the Sixth Conference on Machine Translation (WMT2021) , pages 265–272, Online.
WMT20 Inuktitut-English, Japanese-English, Tamil-English, English-Japanese - 1st place, 1st place, 1st place, 2nd place (Human Evaluation)
The NiuTrans System for the WMT20 Quality Estimation Shared Task. Chi Hu, Hui Liu, Kai Feng, Chen Xu, Nuo Xu, Zefan Zhou, Shiqin Yan, Yingfeng Luo, Chenglong Wang, Xia Meng, Tong Xiao, and Jingbo Zhu. 2020. In Proc. of the Fifth Conference on Machine Translation (WMT2020), pages 1018–1023, Online.
WMT19 Kazakh-English, English-Kazakh, Gujarati-English, German-Czech, Czech-German, Russian-English, English-Russian, Chinese-English, German-English, English-German, Lithuanian-English MT track - 1st place, 1st place, 1st place, 2nd place, 2nd place, 2nd place, 3rd place, 3rd place, 3rd place, 3rd place and 3rd place (BLEU)
The NiuTrans Machine Translation Systems for WMT19, Bei Li, Yinqiao Li, Chen Xu, Ye Lin, Jiqiang Liu, Hui Liu, Ziyang Wang, Yuhao Zhang, Nuo Xu, Zeyang Wang, Kai Feng, Hexuan Chen, Tengbo Liu, YanYang Li, Qiang Wang, Tong Xiao and Jingbo Zhu. In Proc. of the Fourth Conference on Machine Translation (WMT2019), Florence, Italy.
WMT18 Chinese-English, English-Chinese MT track - 2nd place and 2nd place (BLEU)
The NiuTrans Machine Translation System for WMT18, Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao and Jingbo Zhu. In Proc. of the Third Conference on Machine Translation (WMT2018), Brussels, Belgium.
CWMT18 Chinese-English, English-Chinese MT track - 1st place and 2nd place (BLEU)
The NiuTrans Machine Translation System for CWMT-2018, Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao and Jingbo Zhu. In Proc. of the Fourteenth China workshop on Machine Translation (CWMT2018), Fujian, China.
WMT13 Russian-English MT track - 2st/1st place (case-insensitve/sensitive BLEU)
The University of Cambridge Russian-English System at WMT13, Juan Pino, Aurelien Waite, Tong Xiao, Adrià de Gispert, Federico Flego and William Byrne. In Proc. of Proceedings of the Eighth Workshop on Statistical Machine Translation (WMT2013), Sofia, Bulgaria.
NTCIR-9 Chinese-English patent MT track - 2nd place (human evaluation)
The NiuTrans Machine Translation System for NTCIR-9, Tong Xiao, Qiang Li, Qi Lu, Hao Zhang, Haibo Ding, Shujie Yao, Xiaoming Xu, Xiaoxu Fei, Jingbo Zhu, Feiliang Ren and Huizhen Wang. In Proc. of NTCIR-9Workshop Meeting, 2011, Tokyo, Japan.
CWMT2011 English-Chinese and Chinese-English news tracks - 1st place and 4th place (BLEU).
The NiuTrans Machine Translation System for CWMT2011, Tong Xiao, Hao Zhang, Qiang Li, Qi Lu, Jingbo Zhu, Feiliang Ren and Huizhen Wang. In Proc. of The 6th China workshop on Machine Translation (CWMT), 2011, Xiamen, China.
CWMT2009 Chinese-English Single System Track - 2nd place (BLEU)
NEUTrans: a Phrase-Based SMT System for CWMT2009, Tong Xiao, Rushan Chen, Tianning Li, Muhua Zhu, Jingbo Zhu, Huizhen Wang and Feiliang Ren. In Proc. of The 5th China workshop on Machine Translation (CWMT2009), Nanjing, China.
NTCIR-7 English Patent Mining Track - 1st place (MAP)
KNN and Re-ranking Models for English Patent Mining at NTCIR-7, Tong Xiao, Feifei Cao, Tianning Li, Guolong Song, Ke Zhou, Jingbo Zhu and Huizhen Wang. In Proc. of NTCIR-7 Workshop Meeting, 2008, Tokyo, Japan.
开源项目
NiuTrans.SMT: A statistical machine translation system.
NiuTrans.NMT: A lightweight and efficient Transformer-based neural machine translation system.
NiuTensor: An open-source toolkit developed by a joint team from NLP Lab at Northeastern University and the NiuTrans Team. It provides tensor utilities to create and train neural networks.
学术任职
中国中文信息学会理事
中国中文信息学会机器翻译专业委员会委员
中国中文信息学会信息检索与内容安全专业委员会委员
中国中文信息学会青年工作委员会委员
中国计算机学会自然语言处理专委会委员
大会主席: CCMT 2022
领域主席/高级程序委员: ACL 2022/2023/2024, COLING 2018/2022/2024, EMNLP 2020/2022/2023, NAACL 2019/2022, AAAI 2021, IJCAI 2019
期刊审稿人:Transactions of the Association for Computational Linguistics (2021-2024)
期刊审稿人:IEEE Transactions on Audio, Speech and Language Processing (2017-2023)
期刊审稿人:IEEE Transactions on Pattern Analysis and Machine Intelligence (2023-2024)
期刊审稿人:IEEE Transactions on Artificial Intelligent (2023-2024)
期刊审稿人:IEEE Transactions on Circuits and Systems for Video Technology (2023-2024)
期刊审稿人: ACM Transactions on Asian and Low-Resource Language Information Processing (2018-2024)
期刊审稿人:Communications of the ACM (2023-2024)
期刊审稿人:中文信息学报 (2011-2024)
期刊审稿人:计算机学报 (2021-2023)
期刊审稿人:软件学报 (2016-2023)
期刊审稿人:电子学报 (2015-2023)