Long Text Generation via Adversarial Training with Leaked Information

TL;DR

LeakGAN introduces a novel adversarial training framework that leverages leaked high-level features from the discriminator to improve long text generation, effectively capturing sentence structures without supervision.

Contribution

The paper proposes LeakGAN, a new method that enhances GAN-based text generation by incorporating leaked discriminator features into the generator for better long text synthesis.

Findings

LeakGAN outperforms existing models on synthetic and real-world datasets.

It effectively captures sentence structures without supervision.

Improves both long and short text generation quality.

Abstract

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets (GAN) that use a discriminative model to guide the training of the generative model as a reinforcement learning policy has shown promising results in text generation. However, the scalar guiding signal is only available after the entire text has been generated and lacks intermediate information about text structure during the generative process. As such, it limits its success when the length of the generated text samples is long (more than 20 words). In this paper, we propose a new framework, called LeakGAN, to address the problem for long text generation. We allow the discriminative net to leak its own high-level extracted features to the generative net to further help the guidance. The generator incorporates such informative signals into all generation steps through an additional Manager module, which takes the extracted features of current generated words and outputs a latent vector to guide the Worker module for next-word generation. Our extensive experiments on synthetic data and various real-world tasks with Turing test demonstrate that LeakGAN is highly effective in long text generation and also improves the performance in short text generation scenarios. More importantly, without any supervision, LeakGAN would be able to implicitly learn sentence structures only through the interaction between Manager and Worker.