NIPS Proceedingsβ

Noam Shazeer

4 Papers

  • Blockwise Parallel Decoding for Deep Autoregressive Models (2018)
  • Mesh-TensorFlow: Deep Learning for Supercomputers (2018)
  • Attention is All you Need (2017)
  • Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks (2015)