Log In Sign Up

Conditional Hybrid GAN for Sequence Generation

by   Yi Yu, et al.

Conditional sequence generation aims to instruct the generation procedure by conditioning the model with additional context information, which is a self-supervised learning issue (a form of unsupervised learning with supervision information from data itself). Unfortunately, the current state-of-the-art generative models have limitations in sequence generation with multiple attributes. In this paper, we propose a novel conditional hybrid GAN (C-Hybrid-GAN) to solve this issue. Discrete sequence with triplet attributes are separately generated when conditioned on the same context. Most importantly, relational reasoning technique is exploited to model not only the dependency inside each sequence of the attribute during the training of the generator but also the consistency among the sequences of attributes during the training of the discriminator. To avoid the non-differentiability problem in GANs encountered during discrete data generation, we exploit the Gumbel-Softmax technique to approximate the distribution of discrete-valued sequences.Through evaluating the task of generating melody (associated with note, duration, and rest) from lyrics, we demonstrate that the proposed C-Hybrid-GAN outperforms the existing methods in context-conditioned discrete-valued sequence generation.


page 1

page 2

page 3

page 4


Self-Supervised Generative Adversarial Networks

Conditional GANs are at the forefront of natural image synthesis. The ma...

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

As a new way of training generative models, Generative Adversarial Nets ...

Conditional LSTM-GAN for Melody Generation from Lyrics

Melody generation from lyrics has been a challenging research issue in t...

GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution

Generative Adversarial Networks (GAN) have limitations when the goal is ...

Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation

Sequence generative adversarial networks (SeqGAN) have been used to impr...

Attribute-conditioned Layout GAN for Automatic Graphic Design

Modeling layout is an important first step for graphic design. Recently,...

Flow Plugin Network for conditional generation

Generative models have gained many researchers' attention in the last ye...