Issues
- 7
- 3
Neural Discrete Representation Learning
#94 opened by kweonwooj - 1
- 1
- 4
Insertion Transformer: Flexible Sequence Generation via Insertion Operations
#123 opened by kweonwooj - 0
Modeling Recurrence for Transformer
#124 opened by kweonwooj - 2
- 0
Non-Monotonic Sequential Text Generation
#121 opened by kweonwooj - 0
Representation Degeneration Problem in Training Natural Language Generation Models
#119 opened by kweonwooj - 2
- 0
- 0
- 0
Semi-Autoregressive Neural Machine Translation
#115 opened by kweonwooj - 0
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
#114 opened by kweonwooj - 0
Multi-Agent Dual Learning
#113 opened by kweonwooj - 0
- 0
Findings of the Second Workshop on Neural Machine Translation and Generation (WMT 2018)
#111 opened by kweonwooj - 3
Is it possible to set up an organization of so-called 'issue user group/paper'?
#107 opened by szrlee - 2
- 0
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
#110 opened by kweonwooj - 0
- 0
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
#106 opened by kweonwooj - 0
Sogou Neural Machine Translation Systems for WMT17
#105 opened by kweonwooj - 0
- 0
- 0
Word Translation without Parallel Data
#100 opened by kweonwooj - 0
- 0
Training Tips for the Transformer Model
#101 opened by kweonwooj - 0
- 0
- 0
Discrete Autoencoders for Sequence Models
#97 opened by kweonwooj - 0
- 0
- 0
SeaRNN: Training RNNs with Global-Local Losses
#93 opened by kweonwooj - 0
- 0
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
#91 opened by kweonwooj - 0
Snapshot Ensembles: Train 1, Get M for Free
#90 opened by kweonwooj - 0
- 0
- 0
DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
#87 opened by kweonwooj - 0
- 0
Towards Neural Phrase-based Machine Translation
#85 opened by kweonwooj - 0
Convolutional Sequence to Sequence Learning
#84 opened by kweonwooj - 0
Apprentice : Using Knowledge Distillation Techniques to Improve Low-Precision Network Accuracy
#83 opened by kweonwooj - 0
Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
#82 opened by kweonwooj - 0
Distilling the Knowledge in a Neural Network
#79 opened by kweonwooj - 0
- 0
On the Convergence of Adam and Beyond
#80 opened by kweonwooj - 0
Pixel Recurrent Neural Networks
#77 opened by kweonwooj - 0