mlsanityData to 14 Oct 2026

A survey on text generation using generative adversarial networks

arXiv 2212.11119 ↗First posted 20 Dec 2022cs.CL cs.AI cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 34 of its 68 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

34 of 68 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  7. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  8. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 376
  9. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  10. 2017Bridging the Gap Between Value and Policy Based Reinforcement Learningcited by 182
  11. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 117
  12. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
22 more
  1. 2018MaskGAN: Better Text Generation via Filling in the______cited by 89
  2. 2015A Primer on Neural Network Models for Natural Language Processingcited by 76
  3. 2017Adversarial Feature Matching for Text Generationcited by 58
  4. 2017Adversarial Ranking for Language Generationcited by 50
  5. 2016GANS for Sequences of Discrete Elements with the Gumbel-softmax Distributioncited by 48
  6. 2018Toward Diverse Text Generation with Inverse Reinforcement Learningcited by 41
  7. 2018DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Textcited by 40
  8. 2017Maximum-Likelihood Augmented Discrete Generative Adversarial Networkscited by 39
  9. 2020TextGAIL: Generative Adversarial Imitation Learning for Text Generationcited by 28
  10. 2017Boundary-Seeking Generative Adversarial Networkscited by 27
  11. 2018Adversarial Text Generation via Feature-Mover's Distancecited by 27
  12. 2017Language Generation with Recurrent Generative Adversarial Networks without Pre-trainingcited by 14
  13. 2020Self-Adversarial Learning with Comparative Discrimination for Text Generationcited by 11
  14. 2020Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generationcited by 11
  15. 2018BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generationcited by 9
  16. 2018Adversarial Text Generation Without Reinforcement Learningcited by 7
  17. 2019Latent Code and Text-based Generative Adversarial Networks for Soft-text Generationcited by 7
  18. 2017Text Generation Based on Generative Adversarial Nets with Latent Variablecited by 4
  19. 2018Generating Text through Adversarial Training using Skip-Thought Vectorscited by 4
  20. 2019DGSAN: Discrete Generative Self-Adversarial Networkcited by 4
  21. 2020A Survey on Concept Factorization: From Shallow to Deep Representation Learningcited by 4
  22. 2018ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 5; 2026: 1.

16 papers.

Sort:

By area:

  1. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 151
  2. 2023RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Modelcited by 47
  3. 2023PAC-Bayesian Generalization Bounds for Adversarial Generative Modelscited by 13
  4. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  5. 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decodingcited by 10
  6. 2024A Review of Human Emotion Synthesis Based on Generative Technologycited by 7
  7. 2023Gaussian Harmony: Attaining Fairness in Diffusion-based Face Generation Modelscited by 5
  8. 2023A data science and machine learning approach to continuous analysis of Shakespeare's playscited by 2
  9. 2024PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformercited by 2
  10. 2024Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learningcited by 1
  11. 2024Conditional Semi-Supervised Data Augmentation for Spam Message Detection with Low Resource Datacited by 0
  12. 2025VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelitycited by 0
4 more
  1. 2025Prime Convolutional Model: Breaking the Ground for Theoretical Explainabilitycited by 0
  2. 2025Structural System Identification via Validation and Adaptationcited by 0
  3. 2025Learning from Few Samples: A Novel Approach for High-Quality Malcode Generationcited by 0
  4. 2026Generative AI and Federated Learning for Intrusion Detection Systems: A Surveycited by 0