TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks

@article{Liu2018TreeGANSS,
  title={TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks},
  author={Xinyue Liu and Xiangnan Kong and Lei Liu and Kuorong Chiang},
  journal={2018 IEEE International Conference on Data Mining (ICDM)},
  year={2018},
  pages={1140-1145}
}
  • Xinyue Liu, Xiangnan Kong, +1 author Kuorong Chiang
  • Published 2018
  • Computer Science
  • 2018 IEEE International Conference on Data Mining (ICDM)
  • Generative Adversarial Networks (GANs) have shown great capacity on image generation, in which a discriminative model guides the training of a generative model to construct images that resemble real images. [...] Key Method In TreeGAN, the generator employs a recurrent neural network (RNN) to construct a parse tree. Each generated parse tree can then be translated to a valid sequence of the given grammar. The discriminator uses a tree-structured RNN to distinguish the generated trees from real trees. We show…Expand Abstract

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Adversarial Feature Matching for Text Generation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Generative Adversarial Nets

    VIEW 14 EXCERPTS
    HIGHLY INFLUENTIAL

    Image-to-Image Translation with Conditional Adversarial Networks

    VIEW 1 EXCERPT

    StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

    VIEW 1 EXCERPT