Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation

Understand

Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation.

• To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS) or reward at every generation step (REGS) is used to evaluate the goodness of a generated subsequence.
• MCTS is computationally intensive, but the performance of REGS is worse than MCTS.
• In this paper, we propose stepwise GAN (StepGAN), in which the discriminator is modified to automatically assign scores quantifying the goodness of each subsequence at every generation step.