TextGAIL: Generative Adversarial Imitation Learning for Text Generation

Understand

Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts.

• We suspect previous text GANs' inferior performance is due to the lack of a reliable guiding signal in their discriminators.
• To address this problem, we propose a generative adversarial imitation learning framework for text generation that uses large pre-trained language models to provide more reliable reward guidance.
• Our approach uses contrastive discriminator, and proximal policy optimization (PPO) to stabilize and improve text generation performance.