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

## TL;DR

This paper introduces Soft-GAN, a novel text-based GAN approach utilizing autoencoders for continuous sentence representation, and proposes hybrid LATEXT-GAN models that outperform traditional methods in text generation tasks.

## Contribution

The paper presents a new soft-text representation for GAN-based text generation and hybrid models combining latent code and soft-text discriminators, advancing the state of the art.

## Key findings

- Soft-GAN effectively generates coherent soft-texts.
- Hybrid LATEXT-GAN models outperform traditional GANs.
- Experimental validation on SNLI and COCO datasets shows improved results.

## Abstract

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.