.png){kind=icon}
Return
Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2019.2896437.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Generative adversarial network
sequence generation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
5.1
Papers:
2.6K
Citations:
1.1W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
ShareSave
View more