Corpus ID: 29797603

Generating Text via Adversarial Training

@inproceedings{Zhang2016GeneratingTV,
  title={Generating Text via Adversarial Training},
  author={Yizhe Zhang and Zhe Gan and L. Carin},
  year={2016}
}
Generative Adversarial Networks (GANs) have achieved great success in generating realistic synthetic real-valued data. However, the discrete output of language model hinders the application of gradient-based GANs. In this paper we propose a generic framework employing Long short-term Memory (LSTM) and convolutional neural network (CNN) for adversarial training to generate realistic text. Instead of using standard objective of GAN, we match the feature distribution when training the generator… Expand
92 Citations
Adversarial Feature Matching for Text Generation
Text-To-Text Generative Adversarial Networks
Evolutionary Generative Adversarial Networks
A Research on Generative Adversarial Networks Applied to Text Generation
Generative Adversarial Nets for Multiple Text Corpora
News text generation with adversarial deep learning
Generating Text using Generative Adversarial Networks and Quick-Thought Vectors
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 24 REFERENCES
Unrolled Generative Adversarial Networks
Improved Techniques for Training GANs
Generative Adversarial Nets
Generating Sentences from a Continuous Space
Skip-Thought Vectors
A Convolutional Neural Network for Modelling Sentences
Sequence to Sequence Learning with Neural Networks
Convolutional Neural Networks for Sentence Classification
Semi-supervised Sequence Learning
Convolutional Neural Network Architectures for Matching Natural Language Sentences
...
1
2
3
...