# Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation

arXiv: https://arxiv.org/abs/1904.07293 · HTML: https://mlsanity.com/paper/1904.07293/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Towards Generating Real-World Time Series Data](https://mlsanity.com/paper/2111.08386/) (2021)
- [A survey on text generation using generative adversarial networks](https://mlsanity.com/paper/2212.11119/) (2022)
- [Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks](https://mlsanity.com/paper/2310.16955/) (2023)
- [Regularizing Transformers With Deep Probabilistic Layers](https://mlsanity.com/paper/2108.10764/) (2021)
- [SparseGAN: Sparse Generative Adversarial Network for Text Generation](https://mlsanity.com/paper/2103.11578/) (2021)
- [OptAGAN: Entropy-based finetuning on text VAE-GAN](https://mlsanity.com/paper/2109.00239/) (2021)
- [Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Dataset](https://mlsanity.com/paper/2308.13545/) (2023)

## Abstract (arXiv)

Text generation with generative adversarial networks (GANs) can be divided into the text-based and code-based categories according to the type of signals used for discrimination. In this work, we introduce a novel text-based approach called Soft-GAN to effectively exploit GAN setup for text generation. We demonstrate how autoencoders (AEs) can be used for providing a continuous representation of sentences, which we will refer to as soft-text. This soft representation will be used in GAN discrimination to synthesize similar soft-texts. We also propose hybrid latent code and text-based GAN (LATEXT-GAN) approaches with one or more discriminators, in which a combination of the latent code and the soft-text is used for GAN discriminations. We perform a number of subjective and objective experiments on two well-known datasets (SNLI and Image COCO) to validate our techniques. We discuss the results using several evaluation metrics and show that the proposed techniques outperform the traditional GAN-based text-generation methods.