{"id":788897,"date":"2021-10-26T23:28:48","date_gmt":"2021-10-27T06:28:48","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=788897"},"modified":"2021-11-21T08:21:12","modified_gmt":"2021-11-21T16:21:12","slug":"neural-machine-translation-2","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/neural-machine-translation-2\/","title":{"rendered":"Neural Machine Translation"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background bg-gray-200 has-background- card-background--full-bleed\">\n\t\t\t\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 align-self-center\">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 id=\"neural-machine-translation\">Neural Machine Translation<\/h1>\n\n\n\n<p><\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>We are working on neural machine translation, using deep neural networks for machine translation. We&nbsp;<a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/blogs.microsoft.com\/ai\/machine-translation-news-test-set-human-parity\/\">achieved human parity<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>&nbsp;in translating news from Chinese to English.<\/p>\n\n\n\n\n\n<ul class=\"wp-block-list\"><li>Xueqing Wu, Yingce Xia, Jinhua Zhu, Lijun Wu, Shufang Xie and Tao Qin, mixSeq: A Simple Data Augmentation Method for Neural Machine Translation, IWSLT 2021<\/li><li>Xueqing Wu, Lewen Wang, Yingce Xia, Weiqing Liu, Lijun Wu, Shufang Xie, Tao Qin, Tie-Yan Liu, Temporally Correlated Task Scheduling for Sequence Learningv. ICML 2021.<\/li><li>Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai and Tie-Yan Liu, UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost. NAACL 2021.<\/li><li>Rui Wang, Xu Tan, Renqian Luo, Tao Qin and Tie-Yan Liu. A Survey on Low-Resource Neural Machine Translation. IJCAI 2021.<\/li><li>Jinhua Zhu, Lijun Wu, Yingce Xia, Shufang Xie, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu. IOT: Instance-wise Layer Reordering for Transformer Structures. ICLR 2021.<\/li><li>Yang Fan, Yingce Xia, Lijun Wu, Shufang Xie, Weiqing Liu, Jiang Bian, Xiangyang Li, Tao Qin. Learning to Reweight with Deep Interactions. AAAI 2021.<\/li><li>Lijun Wu, Shufang Xie, Yingce Xia, Yang Fan, Tao Qin, Jian-Huang Lai and Tie-Yan Liu, Sequence Generation with Mixed Representations. ICML 2020.<\/li><li>Yang Fan, Fei Tian, Yingce Xia, Tao Qin, Xiangyang Li, and Tie-Yan Liu. Searching Better Architectures for Neural Machine Translation. IEEE\/ACM Transactions on Audio, Speech and Language Processing 2020.<\/li><li>Jinhua Zhu, Yingce Xia, Lijun Wu, Di He, Tao Qin, Wengang Zhou, Houqiang Li, Tie-Yan Liu, Incorporating BERT into Neural Machine Translation, ICLR 2020. <\/li><li>Yiren Wang, Lijun Wu, Yingce Xia, Tao Qin, Cheng Xiang Zhai, Tie-Yan Liu, Transductive Ensemble Learning for Neural Machine Translation, AAAI 2020.<\/li><li>Junliang Guo, Xu Tan, Linli Xu, Tao Qin, Tie-Yan Liu, Enhong Chen, Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation, AAAI 2020.<\/li><li>Yiping Lu, Zhuohan Li, Di He, Zhiqing Sun, Bin Dong, Tao Qin, Liwei Wang, and Tie-Yan Liu, Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View, arXiv preprint arXiv:1906.02762, 2019.<\/li><li>Yiren Wang, Yingce Xia, Fei Tian, Fei Gao, Tao Qin, ChengXiang Zhai, and Tie-Yan Liu, Neural Machine Translation with Soft Prototype, NeurIPS 2019. <\/li><li>Lijun Wu, Yiren Wang, Yingce Xia, Tao Qin, Jianwen Lai, and Tie-Yan Liu, Exploiting Monolingual Data at Scale for Neural Machine Translation. EMNLP 2019.<\/li><li>Xu Tan, Jiale Chen, Di He, Yingce Xia, Tao QIN, and Tie-Yan Liu, Multilingual Neural Machine Translation with Language Clustering. EMNLP 2019.<\/li><li>Lijun Wu, Jinhua Zhu, Fei Gao, Di He, Tao QIN, Jianhuang Lai, and Tie-Yan Liu, Machine Translation With Weakly Paired Documents. EMNLP 2019.<\/li><li>Zhuohan Li, Zi Lin, Di He, Fei Tian, Tao QIN, Liwei WANG, and Tie-Yan Liu, Hint-based Training for Non-AutoRegressive Machine Translation. EMNLP 2019.<\/li><li>Yingce Xia, Xu Tan, et al. Microsoft Research Asia\u2019s Systems for WMT19, the fourth Conference on Machine Translation.<\/li><li>Jinhua Zhu, Fei Gao, Lijun Wu, Yingce Xia, Tao Qin, Wengang Zhou, Xueqi Cheng, and Tie-Yan Liu, Soft Contextual Data Augmentation for Neural Machine Translation, ACL 2019.<\/li><li>Yichong Leng, Xu Tan, Tao QIN, Xiang-Yang Li and Tie-Yan Liu, Unsupervised Pivot Translation for Distant Languages, ACL 2019.<\/li><li>Lijun Wu, Yiren Wang, Yingce Xia, Fei Tian, Fei Gao, Tao QIN and Tie-Yan Liu, Depth Growing for Neural Machine Translation, ACL 2019.,<\/li><li>Chang Xu, Tao Qin, Gang Wang, Tie-Yan Liu, Polygon-Net: A General Framework for Jointly Boosting Multiple Unsupervised Neural Machine Translation Models, IJCAI 2019.<\/li><li>Yiren Wang, Yingce Xia, Tianyu He, Fei Tian, Tao Qin, ChengXiang Zhai, Tie-Yan Liu, Multi-Agent Dual Learning, ICLR 2019.<\/li><li>Xu Tan, Yi Ren, Di He, Tao Qin, Tie-Yan Liu, Multilingual Neural Machine Translation with Knowledge Distillation, ICLR 2019.<\/li><li>Yiren Wang, Fei Tian, Di He, Tao Qin, Chengxiang Zhai, Tie-Yan Liu, Non-Autoregressive Machine Translation with Auxiliary Regularization, AAAI 2019.<\/li><li>Junliang Guo, Xu Tan, Di He, Tao Qin, and Tie-Yan Liu, Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input, AAAI 2019.<\/li><li>Chengyue Gong, Xu Tan, Di He, and Tao Qin, Sentence-wise Smooth Regularization for Sequence to Sequence Learning, AAAI 2019.<\/li><li>Yingce Xia, Tianyu He, Xu Tan, Fei Tian, Di He, and Tao Qin, Tied Transformers: Neural Machine Translation with Shared Encoder and Decoder, AAAI 2019.<\/li><li>Yingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu, and Tie-Yan Liu, Model-Level Dual Learning, ICML 2018.<\/li><li>Tianyu He, Xu Tan, Yingce Xia, Di He, Tao Qin, Zhibo Chen, and Tie-Yan Liu, Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation, NIPS 2018.<\/li><li>Lijun Wu, Fei Tian, Tao Qin, Jianhuang Lai and Tie-Yan Liu, A Study of Reinforcement Learning for Neural Machine Translation, EMNLP 2018.<\/li><li>Lijun Wu, Tan Xu, Di He, Fei Tian, Tao Qin, Jianhuang Lai, and Tie-Yan Liu, Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter, EMNLP 2018.<\/li><li>Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, Jianhuang Lai, and Tie-Yan Liu, Adversarial Neural Machine Translation, ACML 2018.<\/li><li>Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, William Lewis, Mu Li, Shujie Liu, Tie-Yan Liu, Renqian Luo, Arul Menezes, Tao Qin, Frank Seide, Xu Tan, Fei Tian, Lijun Wu, Shuangzhi Wu, Yingce Xia, Dongdong Zhang, Zhirui Zhang, Ming Zhou, Achieving Human Parity on Automatic Chinese to English News Translation, arXiv preprint arXiv:1803.05567, 2018.<\/li><li>Fei Gao, Lijun Wu, Li Zhao, Tao Qin, and Tie-Yan Liu, Efficient Sequence Learning with Group Recurrent Networks, NAACL 2018.<\/li><li>Yanyao Shen, Xu Tan, Di He, Tao QIN, and Tie-Yan Liu, Dense Information Flow for Neural Machine Translation, NAACL 2018. <\/li><li>Yijun Wang, Yingce Xia, Li Zhao, Jiang Bian, Tao Qin, Guiquan Liu, and Tie-Yan Liu, Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization, AAAI 2018.<\/li><li>Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu and Tie-Yan Liu, Dual Supervised Learning,&nbsp; ICML 2017.<\/li><li>Di He, Hanqing Lu, Yingce Xia, Tao Qin, Liwei Wang, and Tie-Yan Liu, Decoding with Value Networks for Neural Machine Translation, NIPS 2017.<\/li><li>Yingce Xia, Jiang Bian, Tao Qin, Tie-Yan Liu, Dual Inference for Machine Learning, IJCAI 2017.<\/li><li>Yingce Xia, Fei Tian, Tao Qin, Nenghai Yu and Tie-Yan Liu, Sequence Generation with Target Attention, ECML 2017.<\/li><li>Di He, Yingce Xia, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, and Wei-Ying Ma, Dual Learning for Machine Translation, NIPS 2016.<\/li><\/ul>\n\n\n","protected":false},"excerpt":{"rendered":"<p>We are working on neural machine translation, using deep neural networks for machine translation. We&nbsp;achieved human parity (opens in new tab)&nbsp;in translating news from Chinese to English. Xueqing Wu, Yingce Xia, Jinhua Zhu, Lijun Wu, Shufang Xie and Tao Qin, mixSeq: A Simple Data Augmentation Method for Neural Machine Translation, IWSLT 2021 Xueqing Wu, Lewen [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-788897","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/788897"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":6,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/788897\/revisions"}],"predecessor-version":[{"id":798589,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/788897\/revisions\/798589"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=788897"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=788897"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=788897"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=788897"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=788897"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}