kweonwooj/papers

Issues

• Deliberation Networks: Sequence Generation Beyond One-Pass Decoding

  #78 opened 7 years ago by kweonwooj
  7

• Neural Discrete Representation Learning

  #94 opened 6 years ago by kweonwooj
  3

• Pay Less Attention with Lightweight and Dynamic Convolutions

  #120 opened 6 years ago by kweonwooj
  1

• Insertion-based Decoding with Automatically Inferred Generation Order

  #122 opened 6 years ago by kweonwooj
  1

• Insertion Transformer: Flexible Sequence Generation via Insertion Operations

  #123 opened 6 years ago by kweonwooj
  4

• Modeling Recurrence for Transformer

  #124 opened 5 years ago by kweonwooj
  0

• Improving Generalization Performance by Switching from Adam to SGD

  #76 opened 7 years ago by kweonwooj
  2

• Non-Monotonic Sequential Text Generation

  #121 opened 6 years ago by kweonwooj
  0

• Representation Degeneration Problem in Training Natural Language Generation Models

  #119 opened 6 years ago by kweonwooj
  0

• 03

  #117 opened 6 years ago by elect000
  2

• Hint-based Training for Non-Autoregressive Translation

  #118 opened 6 years ago by kweonwooj
  0

• Blockwise Parallel Decoding for Deep Autoregressive Models

  #116 opened 6 years ago by kweonwooj
  0

• Semi-Autoregressive Neural Machine Translation

  #115 opened 6 years ago by kweonwooj
  0

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  #114 opened 6 years ago by kweonwooj
  0

• Multi-Agent Dual Learning

  #113 opened 6 years ago by kweonwooj
  0

• Long Short-Term Memory as a Dynamically Computed Element-wise Weighted Sum

  #112 opened 6 years ago by kweonwooj
  0

• Findings of the Second Workshop on Neural Machine Translation and Generation (WMT 2018)

  #111 opened 6 years ago by kweonwooj
  0

• Is it possible to set up an organization of so-called 'issue user group/paper'?

  #107 opened 6 years ago by szrlee
  3

• Accelerating Neural Transformer via an Average Attention Network

  #108 opened 6 years ago by kweonwooj
  2

• Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings

  #110 opened 6 years ago by kweonwooj
  0

• Bag-of-Words as Target for Neural Machine Translation

  #109 opened 6 years ago by kweonwooj
  0

• The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation

  #106 opened 6 years ago by kweonwooj
  0

• Sogou Neural Machine Translation Systems for WMT17

  #105 opened 6 years ago by kweonwooj
  0

• Guiding Neural Machine Translation with Retrieved Translation Pieces

  #104 opened 6 years ago by kweonwooj
  0

• Self-Attention with Relative Position Representations

  #103 opened 6 years ago by kweonwooj
  0

• Word Translation without Parallel Data

  #100 opened 6 years ago by kweonwooj
  0

• Variational Inference & Deep Learning : New Synthesis _ Ch.01

  #102 opened 6 years ago by kweonwooj
  0

• Training Tips for the Transformer Model

  #101 opened 6 years ago by kweonwooj
  0

• Synthetic and Natural Noise Both Break Neural Machine Translation

  #99 opened 6 years ago by kweonwooj
  0

• Achieving Human Parity on Automatic Chinese to English News Translation

  #98 opened 6 years ago by kweonwooj
  0

• Discrete Autoencoders for Sequence Models

  #97 opened 6 years ago by kweonwooj
  0

• Analyzing Uncertainty in Neural Machine Translation

  #96 opened 6 years ago by kweonwooj
  0

• Fast Decoding in Sequence Models Using Discrete Latent Variables

  #95 opened 6 years ago by kweonwooj
  0

• SeaRNN: Training RNNs with Global-Local Losses

  #93 opened 6 years ago by kweonwooj
  0

• Reward Augmented Maximum Likelihood for Neural Structured Prediction

  #92 opened 7 years ago by kweonwooj
  0

• Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

  #91 opened 7 years ago by kweonwooj
  0

• Snapshot Ensembles: Train 1, Get M for Free

  #90 opened 7 years ago by kweonwooj
  0

• Sequence Level Training with Recurrent Neural Networks

  #89 opened 7 years ago by kweonwooj
  0

• Cyclical Learning Rates for Training Neural Networks

  #88 opened 7 years ago by kweonwooj
  0

• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding

  #87 opened 7 years ago by kweonwooj
  0

• Compressing Word Embeddings via Deep Compositional Code Learning

  #86 opened 7 years ago by kweonwooj
  0

• Towards Neural Phrase-based Machine Translation

  #85 opened 7 years ago by kweonwooj
  0

• Convolutional Sequence to Sequence Learning

  #84 opened 7 years ago by kweonwooj
  0

• Apprentice : Using Knowledge Distillation Techniques to Improve Low-Precision Network Accuracy

  #83 opened 7 years ago by kweonwooj
  0

• Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling

  #82 opened 7 years ago by kweonwooj
  0

• Distilling the Knowledge in a Neural Network

  #79 opened 7 years ago by kweonwooj
  0

• Model Compression via Distillation and Quantization

  #81 opened 7 years ago by kweonwooj
  0

• On the Convergence of Adam and Beyond

  #80 opened 7 years ago by kweonwooj
  0

• Pixel Recurrent Neural Networks

  #77 opened 7 years ago by kweonwooj
  0

• Data Augmentation for Low-Resource Neural Machine Translation

  #75 opened 7 years ago by kweonwooj
  0