Melvin Johnson

The Missing Ingredient in Zero-Shot Neural Machine Translation pdf

Ankur Bapna, Naveen Arivazhagan, Orhan Firat, 2019, ArXiv.

Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation

Yuan Cao, Melvin Johnson, Wolfgang Macherey, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Martin Wattenberg, Quoc V. Le, Yonghui Wu, 2016, TACL.

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling pdf

Tara N. Sainath, Ankur Bapna, Navdeep Jaitly, 2019, ArXiv.

Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation pdf

Orhan Firat, Melvin Johnson, Wolfgang Macherey, 2018, ArXiv.

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation pdf

George Kurian, Wei Wang, Quoc V. Le, 2016, ArXiv.

ENHANCING RIGHT-OF-WAY HERBICIDE TREATMENTS /

Melvin Johnson, Rita L. McKenzie, Harvey H. Holt, 1995 .

Direct speech-to-speech translation with a sequence-to-sequence model

Melvin Johnson, Wolfgang Macherey, Fadi Biadsy, 2019, INTERSPEECH.

HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints

Melvin Johnson, Aravindan Raghuveer, Sahana Ramnath, 2021, EMNLP.

SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training pdf

Ankur Bapna, Melvin Johnson, Ye Jia, 2021, ArXiv.

Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents pdf

Ankur Bapna, Naveen Arivazhagan, Orhan Firat, 2021, ArXiv.

DOCmT5: Document-Level Pretraining of Multilingual Language Models pdf

Melvin Johnson, Aditya Siddhant, Viresh Ratnakar, 2021, ArXiv.