Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
arXiv:1808.05599
Abstract
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. StepGAN has significantly less computational costs than MCTS. We demonstrate that StepGAN outperforms previous GAN-based methods on both synthetic experiment and chit-chat dialogue generation.
References in corpus (16)
- Playing Atari with Deep Reinforcement Learning
- Convolutional Sequence to Sequence Learning
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- A Neural Conversational Model
- Improved Training of Wasserstein GANs
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Deep Reinforcement Learning for Dialogue Generation
- An Actor-Critic Algorithm for Sequence Prediction
- Adversarial Learning for Neural Dialogue Generation
- GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
- Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
- Adversarial Feature Matching for Text Generation
- Adversarial Generation of Natural Language
- Language Generation with Recurrent Generative Adversarial Networks without Pre-training
- Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning
- Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training