Yonghui Wu
First author of the paper on Google's Neural Machine Translation system (GNMT); co-author of Lingvo
Yonghui Wu is the first author of the 2016 paper presenting GNMT, Google's Neural Machine Translation system, which describes deep LSTM encoder and decoder networks with attention for translation and thanks the Google Brain and Google Translate teams. Wu is also a co-author of the 2019 paper on Lingvo, a TensorFlow framework for sequence-to-sequence modeling published in the TensorFlow GitHub organization under the Apache 2.0 license.123
Work
Google's Neural Machine Translation system (GNMT) (external site: arxiv.org)Published research
First author of the 2016 paper presenting GNMT, a translation model built from a deep LSTM network with eight encoder and eight decoder layers and an attention mechanism, using sub-word units called wordpieces.1
Lingvo (external site: github.com)Open-source code
Co-author of the 2019 Lingvo paper; Lingvo is a framework for building neural networks in TensorFlow, particularly sequence models, released under the Apache 2.0 license.23
Other documented roles
Roles the sources document but that are not confirmed as current.
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.