Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation

08/16/2018
by   Yi-Lin Tuan, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/16/2020

OptiGAN: Generative Adversarial Networks for Goal Optimized Sequence Generation

One of the challenging problems in sequence generation tasks is the opti...
09/24/2019

Keyphrase Generation for Scientific Articles using GANs

In this paper, we present a keyphrase generation approach using conditio...
07/22/2021

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

We propose a methodology to approximate conditional distributions in the...
04/05/2020

Game of Learning Bloch Equation Simulations for MR Fingerprinting

Purpose: This work proposes a novel approach to efficiently generate MR ...
03/25/2021

Generative-Adversarial-Networks-based Ghost Recognition

Nowadays, target recognition technique plays an important role in many f...
03/26/2023

Query Generation based on Generative Adversarial Networks

Many problems in database systems, such as cardinality estimation, datab...
12/30/2022

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