Corpus ID: 29797603

Generating Text via Adversarial Training

@inproceedings{Zhang2016GeneratingTV,
  title={Generating Text via Adversarial Training},
  author={Yizhe Zhang and Zhe Gan and Lawrence Carin},
  year={2016}
}
  • Yizhe Zhang, Zhe Gan, Lawrence Carin
  • Published 2016
  • Computer Science
  • 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… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 73 CITATIONS

    Adversarial Feature Matching for Text Generation

    VIEW 2 EXCERPTS
    CITES METHODS

    Text-To-Text Generative Adversarial Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Evolutionary Generative Adversarial Networks

    VIEW 1 EXCERPT
    CITES BACKGROUND

    A Research on Generative Adversarial Networks Applied to Text Generation

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Generative Adversarial Nets for Multiple Text Corpora

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    News text generation with adversarial deep learning

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Generating Text using Generative Adversarial Networks and Quick-Thought Vectors

    VIEW 1 EXCERPT
    CITES METHODS

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 10 Highly Influenced Citations

    • Averaged 19 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 19 REFERENCES

    Improved Techniques for Training GANs

    VIEW 3 EXCERPTS

    Generative Adversarial Nets

    VIEW 3 EXCERPTS

    Generating Sentences from a Continuous Space

    VIEW 2 EXCERPTS

    Skip-Thought Vectors

    VIEW 2 EXCERPTS

    Convolutional Neural Networks for Sentence Classification

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Semi-supervised Sequence Learning

    VIEW 1 EXCERPT