387 citations · 1.4k across the 16 of their papers we have counts for
7 papers · 1 filter
Mesh-TensorFlow: Deep Learning for Supercomputers
Noam Shazeer, Youlong Cheng, Niki Parmar +9
Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program…
Weakly Supervised Grammatical Error Correction using Iterative Decoding
Jared Lichtarge, Christopher Alberti, Shankar Kumar +2
We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transform…
Theory and Experiments on Vector Quantized Autoencoders
Aurko Roy, Ashish Vaswani, Arvind Neelakantan +1
Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a su…
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
Mia Xu Chen, Orhan Firat, Ankur Bapna +9
The past year has witnessed rapid advances in sequence-to-sequence (seq2seq) modeling for Machine Translation (MT). The classic RNN-based approaches to MT were first out-performed…
Tensor2Tensor for Neural Machine Translation
Ashish Vaswani, Samy Bengio, Eugene Brevdo +10
Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer…
Fast Decoding in Sequence Models using Discrete Latent Variables
Łukasz Kaiser, Aurko Roy, Ashish Vaswani +4
Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult t…
Image Transformer
Niki Parmar, Ashish Vaswani, Jakob Uszkoreit +4
Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of mod…