Corpus ID: 13895969

Neural Machine Translation in Linear Time

@article{Kalchbrenner2016NeuralMT,
  title={Neural Machine Translation in Linear Time},
  author={Nal Kalchbrenner and Lasse Espeholt and K. Simonyan and A. Oord and A. Graves and K. Kavukcuoglu},
  journal={ArXiv},
  year={2016},
  volume={abs/1610.10099}
}
  • Nal Kalchbrenner, Lasse Espeholt, +3 authors K. Kavukcuoglu
  • Published 2016
  • Computer Science
  • ArXiv
  • We present a novel neural network for processing sequences. [...] Key Method To address the differing lengths of the source and the target, we introduce an efficient mechanism by which the decoder is dynamically unfolded over the representation of the encoder. The ByteNet uses dilation in the convolutional layers to increase its receptive field. The resulting network has two core properties: it runs in time that is linear in the length of the sequences and it sidesteps the need for excessive memorization. The…Expand Abstract
    Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU
    • 28
    • PDF
    A Convolutional Encoder Model for Neural Machine Translation
    • 227
    • PDF
    Attention is All you Need
    • 11,984
    • PDF
    Weighted Transformer Network for Machine Translation
    • 76
    • PDF
    Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
    • 45
    • PDF
    Fast-Slow Recurrent Neural Networks
    • 54
    • PDF
    Re-encoding in Neural Machine Translation
    • Johannes Baptist
    • 2017
    Towards Linear Time Neural Machine Translation with Capsule Networks
    • 14
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 51 REFERENCES
    Neural Machine Translation by Jointly Learning to Align and Translate
    • 12,953
    • Highly Influential
    • PDF
    A Character-level Decoder without Explicit Segmentation for Neural Machine Translation
    • 262
    • PDF
    Sequence to Sequence Learning with Neural Networks
    • 10,558
    • Highly Influential
    • PDF
    Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
    • 2,885
    • PDF
    Grid Long Short-Term Memory
    • 266
    • PDF
    Effective Approaches to Attention-based Neural Machine Translation
    • 3,933
    • PDF
    Recurrent Continuous Translation Models
    • 998
    • PDF