Modeling documents with Generative Adversarial Networks

Abstract

This paper describes a method for using Generative Adversarial Networks to learn distributed representations of natural language documents. We propose a model that is based on the recently proposed Energy-Based GAN, but instead uses a Denoising Autoencoder as the discriminator network. Document representations are extracted from the hidden layer of the discriminator and evaluated both quantitatively and qualitatively.

References in corpus (2)

• DRAW: A Recurrent Neural Network For Image Generation
• Energy-based Generative Adversarial Network

Cited by in corpus (3)

• Adversarial Network Embedding
• eCommerceGAN : A Generative Adversarial Network for E-commerce
• Generative Adversarial Nets for Multiple Text Corpora