Convolutional Sequence to Sequence Learning

by   Jonas Gehring, et al.

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.


Context- and Sequence-Aware Convolutional Recurrent Encoder for Neural Machine Translation

Neural Machine Translation model is a sequence-to-sequence converter bas...

Dynamic Prediction Length for Time Series with Sequence to Sequence Networks

Recurrent neural networks and sequence to sequence models require a pred...

On the Universality of Linear Recurrences Followed by Nonlinear Projections

In this note (work in progress towards a full-length paper) we show that...

Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation

Memory-efficient continuous Sign Language Translation is a significant c...

Recurrent autoencoder with sequence-aware encoding

Recurrent Neural Networks (RNN) received a vast amount of attention last...

Pointer Networks

We introduce a new neural architecture to learn the conditional probabil...

Classical Structured Prediction Losses for Sequence to Sequence Learning

There has been much recent work on training neural attention models at t...

Code Repositories


Facebook AI Research Sequence-to-Sequence Toolkit

view repo


Framework to imitate writing styles using deep learning

view repo


A quick Tensorflow implementation of Facebook FairSeq[1] for character-level neural machine translation (EN -> JP).

view repo

Please sign up or login with your details

Forgot password? Click here to reset