Small and Practical BERT Models for Sequence Labeling EMNLP

Henry Tsai | Jason Riesa | Melvin Johnson | Naveen Arivazhagan | Xin Li | Amelia Archer |

Massively Multilingual Neural Machine Translation NAACL

Roee Aharoni | Melvin Johnson | Orhan Firat |

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation ACL

Mia Xu Chen | Orhan Firat | Ankur Bapna | Melvin Johnson | Wolfgang Macherey | George Foster | Llion Jones | Mike Schuster | Noam Shazeer | Niki Parmar | Ashish Vaswani | Jakob Uszkoreit | Lukasz Kaiser | Zhifeng Chen | Yonghui Wu | Macduff Hughes |

Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation TACL

Melvin Johnson | Mike Schuster | Quoc V. Le | Maxim Krikun | Yonghui Wu | Zhifeng Chen | Nikhil Thorat | Fernanda Viégas | Martin Wattenberg | Greg Corrado | Macduff Hughes | Jeffrey Dean |