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.
Abstract (translated)
产生性对抗网络(gans)的文本生成可以根据识别信号的类型分为基于文本和基于代码的两类。在这项工作中,我们引入了一种新的基于文本的方法,称为软gan,以有效地利用gan设置来生成文本。我们将演示如何使用自动编码器(aes)来提供句子的连续表示,我们将其称为软文本。这种软表示将被用于GAN识别,以合成类似的软文本。我们还提出了混合潜码和基于文本的gan(latext-gan)方法,其中潜码和软文本的组合用于gan识别。我们对两个著名的数据集(snli和image coco)进行了一些主观和客观实验,以验证我们的技术。我们使用几种评估指标对结果进行了讨论,结果表明,所提出的技术优于传统的基于氮化镓的文本生成方法。
URL
https://arxiv.org/abs/1904.07293