Corpus ID: 3730033

Dual Supervised Learning

@article{Xia2017DualSL,
  title={Dual Supervised Learning},
  author={Yingce Xia and Tao Qin and Wei Chen and Jiang Bian and Nenghai Yu and Tie-Yan Liu},
  journal={ArXiv},
  year={2017},
  volume={abs/1707.00415}
}
Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between their models. This connection is, however, not effectively utilized today, since people usually train the models of two dual tasks separately and independently. In this work, we… Expand
Dual Inference for Machine Learning
Model-Level Dual Learning
Zero-Shot Dual Machine Translation
Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization
Towards Unsupervised Language Understanding and Generation by Joint Dual Learning
Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
Dual supervised learning for non-native speech recognition
Reciprocal Supervised Learning Improves Neural Machine Translation
MIRROR-GENERATIVE NEURAL MACHINE TRANSLA-
  • 2019
Semantic Parser and Natural Language Generator via Dual Information Maximization
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Dual Inference for Machine Learning
Dual Learning for Machine Translation
Semi-supervised Sequence Learning
Attention is All you Need
Neural Machine Translation by Jointly Learning to Align and Translate
LSTM Neural Networks for Language Modeling
...
1
2
3
4
5
...