Adversarial Generation of Natural Language

Abstract

Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation. Advances in the adversarial generation of natural language from noise however are not commensurate with the progress made in generating images, and still lag far behind likelihood based methods. In this paper, we take a step towards generating natural language with a GAN objective alone. We introduce a simple baseline that addresses the discrete output space problem without relying on gradient estimators and show that it is able to achieve state-of-the-art results on a Chinese poem generation dataset. We present quantitative results on generating sentences from context-free and probabilistic context-free grammars, and qualitative language modeling results. A conditional version is also described that can generate sequences conditioned on sentence characteristics.

11 pages, 3 figures, 5 tables

References in corpus (6)

• Conditional Generative Adversarial Nets
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Recurrent Neural Network Regularization
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• Mode Regularized Generative Adversarial Networks
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

Cited by in corpus (7)

• Long Text Generation via Adversarial Training with Leaked Information
• Recent Advances of Image Steganography with Generative Adversarial Networks
• ACtuAL: Actor-Critic Under Adversarial Learning
• Automatic Repair and Type Binding of Undeclared Variables using Neural Networks
• Adversarial Sub-sequence for Text Generation
• Generative Adversarial Nets for Multiple Text Corpora
• Evaluating Computational Language Models with Scaling Properties of Natural Language