Alert button
Picture for Wolfgang Macherey

Wolfgang Macherey

Alert button

AdvAug: Robust Adversarial Augmentation for Neural Machine Translation

Jun 28, 2020
Yong Cheng, Lu Jiang, Wolfgang Macherey, Jacob Eisenstein

Figure 1 for AdvAug: Robust Adversarial Augmentation for Neural Machine Translation
Figure 2 for AdvAug: Robust Adversarial Augmentation for Neural Machine Translation
Figure 3 for AdvAug: Robust Adversarial Augmentation for Neural Machine Translation
Figure 4 for AdvAug: Robust Adversarial Augmentation for Neural Machine Translation
Viaarxiv icon

Re-translation versus Streaming for Simultaneous Translation

Apr 14, 2020
Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, George Foster

Figure 1 for Re-translation versus Streaming for Simultaneous Translation
Figure 2 for Re-translation versus Streaming for Simultaneous Translation
Figure 3 for Re-translation versus Streaming for Simultaneous Translation
Figure 4 for Re-translation versus Streaming for Simultaneous Translation
Viaarxiv icon

Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation

Dec 06, 2019
Naveen Arivazhagan, Colin Cherry, Te I, Wolfgang Macherey, Pallavi Baljekar, George Foster

Figure 1 for Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation
Figure 2 for Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation
Figure 3 for Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation
Figure 4 for Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation
Viaarxiv icon

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

Jul 11, 2019
Naveen Arivazhagan, Ankur Bapna, Orhan Firat, Dmitry Lepikhin, Melvin Johnson, Maxim Krikun, Mia Xu Chen, Yuan Cao, George Foster, Colin Cherry, Wolfgang Macherey, Zhifeng Chen, Yonghui Wu

Figure 1 for Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Figure 2 for Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Figure 3 for Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Figure 4 for Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Viaarxiv icon

Monotonic Infinite Lookback Attention for Simultaneous Machine Translation

Jun 12, 2019
Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, Chung-Cheng Chiu, Semih Yavuz, Ruoming Pang, Wei Li, Colin Raffel

Figure 1 for Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
Figure 2 for Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
Viaarxiv icon

Robust Neural Machine Translation with Doubly Adversarial Inputs

Jun 06, 2019
Yong Cheng, Lu Jiang, Wolfgang Macherey

Figure 1 for Robust Neural Machine Translation with Doubly Adversarial Inputs
Figure 2 for Robust Neural Machine Translation with Doubly Adversarial Inputs
Figure 3 for Robust Neural Machine Translation with Doubly Adversarial Inputs
Figure 4 for Robust Neural Machine Translation with Doubly Adversarial Inputs
Viaarxiv icon

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

Apr 12, 2019
Ye Jia, Ron J. Weiss, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, Yonghui Wu

Figure 1 for Direct speech-to-speech translation with a sequence-to-sequence model
Figure 2 for Direct speech-to-speech translation with a sequence-to-sequence model
Figure 3 for Direct speech-to-speech translation with a sequence-to-sequence model
Figure 4 for Direct speech-to-speech translation with a sequence-to-sequence model
Viaarxiv icon

The Missing Ingredient in Zero-Shot Neural Machine Translation

Mar 17, 2019
Naveen Arivazhagan, Ankur Bapna, Orhan Firat, Roee Aharoni, Melvin Johnson, Wolfgang Macherey

Figure 1 for The Missing Ingredient in Zero-Shot Neural Machine Translation
Figure 2 for The Missing Ingredient in Zero-Shot Neural Machine Translation
Figure 3 for The Missing Ingredient in Zero-Shot Neural Machine Translation
Figure 4 for The Missing Ingredient in Zero-Shot Neural Machine Translation
Viaarxiv icon