A survey on text generation using generative adversarial networks

Abstract

This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called "natural" language. Nevertheless, adversarial text generation is not a simple task as its foremost architecture, the Generative Adversarial Networks, were designed to cope with continuous information (image) instead of discrete data (text). Thus, most works are based on three possible options, i.e., Gumbel-Softmax differentiation, Reinforcement Learning, and modified training objectives. All alternatives are reviewed in this survey as they present the most recent approaches for generating text using adversarial-based techniques. The selected works were taken from renowned databases, such as Science Direct, IEEEXplore, Springer, Association for Computing Machinery, and arXiv, whereas each selected work has been critically analyzed and assessed to present its objective, methodology, and experimental results.

References in corpus (14)

• Categorical Reparameterization with Gumbel-Softmax
• Improved Training of Wasserstein GANs
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• MaskGAN: Better Text Generation via Filling in the______
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Bridging the Gap Between Value and Policy Based Reinforcement Learning
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• Long Text Generation via Adversarial Training with Leaked Information
• Boundary-Seeking Generative Adversarial Networks
• Adversarial Text Generation via Feature-Mover's Distance
• Toward Diverse Text Generation with Inverse Reinforcement Learning
• BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation
• Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
• ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANs

Cited by in corpus (4)

• A Systematic Survey of Regularization and Normalization in GANs
• Controllable Data Generation by Deep Learning: A Review
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• A data science and machine learning approach to continuous analysis of Shakespeare's plays