papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-04-15
Md. Akmal Haidar, Mehdi Rezagholizadeh, Alan Do-Omri, Ahmad Rashid

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 by Google)
URL

http://arxiv.org/abs/1904.07293

PDF

http://arxiv.org/pdf/1904.07293


Comments

Content