Corpus ID: 7961699

Sequence to Sequence Learning with Neural Networks

@article{Sutskever2014SequenceTS,
  title={Sequence to Sequence Learning with Neural Networks},
  author={Ilya Sutskever and Oriol Vinyals and Quoc V. Le},
  journal={ArXiv},
  year={2014},
  volume={abs/1409.3215}
}
  • Ilya Sutskever, Oriol Vinyals, Quoc V. Le
  • Published 2014
  • Computer Science
  • ArXiv
  • Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. [...] Key Method Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT-14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set…Expand Abstract
    Effective Approaches to Attention-based Neural Machine Translation
    • 3,873
    • Highly Influenced
    • Open Access
    Show and tell: A neural image caption generator
    • 3,389
    • Open Access
    Attention is All you Need
    • 11,441
    • Open Access
    Neural Machine Translation by Jointly Learning to Align and Translate
    • 12,759
    • Highly Influenced
    • Open Access
    Neural Architecture Search with Reinforcement Learning
    • 1,902
    • Open Access
    TensorFlow: A system for large-scale machine learning
    • 7,594
    • Open Access
    Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
    • 2,825
    • Open Access
    Neural Machine Translation of Rare Words with Subword Units
    • 2,674
    • Open Access
    Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
    • 4,519
    • Open Access
    Long-term recurrent convolutional networks for visual recognition and description
    • 3,178
    • Highly Influenced
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES
    ImageNet classification with deep convolutional neural networks
    • 51,779
    • Open Access
    ImageNet Classification with Deep Convolutional Neural Networks
    • 51,779
    • Open Access
    Long Short-Term Memory
    • 30,504
    • Open Access
    Neural Machine Translation by Jointly Learning to Align and Translate
    • 12,759
    • Open Access
    Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
    • 9,395
    • Highly Influential
    • Open Access
    Gradient-based learning applied to document recognition
    • 24,118
    • Open Access
    Efficient Estimation of Word Representations in Vector Space
    • 14,974
    • Open Access
    Learning representations by back-propagating errors
    • 15,863
    • Highly Influential
    • Open Access
    Learning long-term dependencies with gradient descent is difficult
    • 4,476
    • Open Access
    Recurrent neural network based language model
    • 3,929
    • Open Access