MJ
Melvin Johnson
cs.CLcs.AIcs.LGcs.SDeess.AScs.CVstat.ML
On Valency
published · living versionsW_zb7r6dq8·v1 · currentpublished
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
with Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le +26
1 version
Preprints & journals
36 papers in the corpus · 2016–2026Gemma 4 Technical Report2607.02770v2 · Gemma Team: Sherif El Abd, Vaibhav Aggarwal, Robin Algayres et al.2026 · 3 citationsarXiv
Gemini: A Family of Highly Capable Multimodal Models2312.11805v5 · Gemini Team Google: Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.2023 · 838 citationsarXiv
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context2403.05530v5 · Gemini Team Google: Petko Georgiev, Ving Ian Lei, Ryan Burnell et al.2024 · 296 citationsarXiv
Capabilities of Gemini Models in Medicine2404.18416v2 · Khaled Saab, Tao Tu, Wei-Hung Weng et al.2024 · 98 citationsarXiv
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages2305.11938v2 · Sebastian Ruder, Jonathan H. Clark, Alexander Gutkin et al.2023 · 15 citationsarXiv
PaLM 2 Technical Report2305.10403v3 · Rohan Anil, Andrew M. Dai, Orhan Firat et al.2023 · 161 citationsarXiv
Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models2212.09553v2 · Yong Cheng, Yu Zhang, Melvin Johnson et al.2022 · 5 citationsarXiv
The unreasonable effectiveness of few-shot learning for machine translation2302.01398v1 · Xavier Garcia, Yamini Bansal, Colin Cherry et al.2023 · 24 citationsarXiv
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents2109.10341v2 · Biao Zhang, Ankur Bapna, Melvin Johnson et al.2021 · 6 citationsarXiv
DOCmT5: Document-Level Pretraining of Multilingual Language Models2112.08709v2 · Chia-Hsuan Lee, Aditya Siddhant, Viresh Ratnakar et al.2021 · 5 citationsarXiv
XTREME-S: Evaluating Cross-lingual Speech Representations2203.10752v3 · Alexis Conneau, Ankur Bapna, Yu Zhang et al.2022 · 17 citationsarXiv
mSLAM: Massively multilingual joint pre-training for speech and text2202.01374v1 · Ankur Bapna, Colin Cherry, Yu Zhang et al.2022 · 59 citationsarXiv
SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training2110.10329v1 · Ankur Bapna, Yu-an Chung, Nan Wu et al.2021 · 49 citationsarXiv
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation2104.07412v2 · Sebastian Ruder, Noah Constant, Jan Botha et al.2021 · 118 citationsarXiv
HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints2109.04443v1 · Sahana Ramnath, Melvin Johnson, Abhirut Gupta et al.2021 · 8 citationsarXiv
MergeDistill: Merging Pre-trained Language Models using Distillation2106.02834v1 · Simran Khanuja, Melvin Johnson, Partha Talukdar2021 · 1 citationarXiv
nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?2106.02171v1 · Mihir Kale, Aditya Siddhant, Noah Constant et al.2021 · 10 citationsarXiv
Explicit Alignment Objectives for Multilingual Bidirectional Encoders2010.07972v2 · Junjie Hu, Melvin Johnson, Orhan Firat et al.2020 · 47 citationsarXiv
Gradient-guided Loss Masking for Neural Machine Translation2102.13549v1 · Xinyi Wang, Ankur Bapna, Melvin Johnson et al.2021 · 11 citationsarXiv
They, Them, Theirs: Rewriting with Gender-Neutral English2102.06788v1 · Tony Sun, Kellie Webster, Apu Shah et al.2021 · 28 citationsarXiv
Distilling Large Language Models into Tiny and Effective Students using pQRNN2101.08890v1 · Prabhu Kaliamoorthi, Aditya Siddhant, Edward Li et al.2021 · 17 citationsarXiv
Rethinking embedding coupling in pre-trained language models2010.12821v1 · Hyung Won Chung, Thibault F'evry, Henry Tsai et al.2020 · 11 citationsarXiv
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization2003.11080v5 · Junjie Hu, Sebastian Ruder, Aditya Siddhant et al.2020 · 295 citationsarXiv
Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation1909.00437v1 · Aditya Siddhant, Melvin Johnson, Henry Tsai et al.2019 · 70 citationsAAAI 2020
Adaptive Scheduling for Multi-Task Learning1909.06434v1 · S'ebastien Jean, Orhan Firat, Melvin Johnson2019 · 31 citationsarXiv
Small and Practical BERT Models for Sequence Labeling1909.00100v1 · Henry Tsai, Jason Riesa, Melvin Johnson et al.2019 · 137 citationsarXiv
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges1907.05019v1 · Naveen Arivazhagan, Ankur Bapna, Orhan Firat et al.2019 · 287 citationsarXiv
Massively Multilingual Neural Machine Translation1903.00089v3 · Roee Aharoni, Melvin Johnson, Orhan Firat2019 · 458 citationsarXiv
Direct speech-to-speech translation with a sequence-to-sequence model1904.06037v2 · Ye Jia, Ron J. Weiss, Fadi Biadsy et al.2019 · 197 citationsarXiv
The Missing Ingredient in Zero-Shot Neural Machine Translation1903.07091v1 · Naveen Arivazhagan, Ankur Bapna, Orhan Firat et al.2019 · 92 citationsarXiv
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling1902.08295v1 · Jonathan Shen, Patrick Nguyen, Yonghui Wu et al.2019 · 181 citationsarXiv
Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation1811.02050v2 · Ye Jia, Melvin Johnson, Wolfgang Macherey et al.2018 · 158 citationsarXiv
Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation1809.04686v1 · Akiko Eriguchi, Melvin Johnson, Orhan Firat et al.2018 · 78 citationsarXiv
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation1804.09849v2 · Mia Xu Chen, Orhan Firat, Ankur Bapna et al.2018 · 466 citationsarXiv
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation1611.04558v2 · Melvin Johnson, Mike Schuster, Quoc V. Le et al.2016 · 1,873 citationsarXiv
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation1609.08144v2 · Yonghui Wu, Mike Schuster, Zhifeng Chen et al.2016 · 5,573 citationsarXivon Valency
Career total: 52 works. 36 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.