Text Generation with Deep Variational GAN
arXiv:2104.13488
Abstract
Generating realistic sequences is a central task in many machine learning applications. There has been considerable recent progress on building deep generative models for sequence generation tasks. However, the issue of mode-collapsing remains a main issue for the current models. In this paper we propose a GAN-based generic framework to address the problem of mode-collapse in a principled approach. We change the standard GAN objective to maximize a variational lower-bound of the log-likelihood while minimizing the Jensen-Shanon divergence between data and model distributions. We experiment our model with text generation task and show that it can generate realistic text with high diversity.
arXiv commentAccepted in the Third Workshop on Bayesian Deep Learning (NIPS / NeurIPS 2018)
References in corpus (7)
- Auto-Encoding Variational Bayes
- Categorical Reparameterization with Gumbel-Softmax
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Autoencoding beyond pixels using a learned similarity metric
- MaskGAN: Better Text Generation via Filling in the______
- Adversarial Feature Matching for Text Generation
- Improved generator objectives for GANs