Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder EMNLP

Shuqi Lu | Di He | Chenyan Xiong | Guolin Ke | Waleed Malik | Zhicheng Dou | Paul Bennett | Tie-Yan Liu | Arnold Overwijk |

Multilingual Neural Machine Translation with Language Clustering EMNLP

Xu Tan | Jiale Chen | Di He | Yingce Xia | Tao QIN | Tie-Yan Liu |

Machine Translation With Weakly Paired Documents EMNLP

Lijun Wu | Jinhua Zhu | Di He | Fei Gao | Tao QIN | Jianhuang Lai | Tie-Yan Liu |

Hint-Based Training for Non-Autoregressive Machine Translation EMNLP

Zhuohan Li | Zi Lin | Di He | Fei Tian | Tao QIN | Liwei WANG | Tie-Yan Liu |

Microsoft Research Asia’s Systems for WMT19 ACL WMT WS

Yingce Xia | Xu Tan | Fei Tian | Fei Gao | Di He | Weicong Chen | Yang Fan | Linyuan Gong | Yichong Leng | Renqian Luo | Yiren Wang | Lijun Wu | Jinhua Zhu | Tao Qin | Tie-Yan Liu |

Double Path Networks for Sequence to Sequence Learning COLING

Kaitao Song | Xu Tan | Di He | Jianfeng Lu | Tao Qin | Tie-Yan Liu |

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter EMNLP

Lijun Wu | Xu Tan | Di He | Fei Tian | Tao Qin | Jianhuang Lai | Tie-Yan Liu |

Dense Information Flow for Neural Machine Translation NAACL

Yanyao Shen | Xu Tan | Di He | Tao Qin | Tie-Yan Liu |