Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation

by   Yi-Lin Tuan, et al.

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.


page 1

page 2

page 3

page 4


OptiGAN: Generative Adversarial Networks for Goal Optimized Sequence Generation

One of the challenging problems in sequence generation tasks is the opti...

Keyphrase Generation for Scientific Articles using GANs

In this paper, we present a keyphrase generation approach using conditio...

cCorrGAN: Conditional Correlation GAN for Learning Empirical Conditional Distributions in the Elliptope

We propose a methodology to approximate conditional distributions in the...

Game of Learning Bloch Equation Simulations for MR Fingerprinting

Purpose: This work proposes a novel approach to efficiently generate MR ...

Generative-Adversarial-Networks-based Ghost Recognition

Nowadays, target recognition technique plays an important role in many f...

Query Generation based on Generative Adversarial Networks

Many problems in database systems, such as cardinality estimation, datab...

Modified Query Expansion Through Generative Adversarial Networks for Information Extraction in E-Commerce

This work addresses an alternative approach for query expansion (QE) usi...

Please sign up or login with your details

Forgot password? Click here to reset