Tuesday, January 4, 2022

OptAGAN: Entropy-based Finetuning on Text VAE-GAN

 

Author :  Paolo Tirotta

Affiliation :  University of Bologna

Country :  Italy

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  11, 23, December, 2021

Abstract :


Transfer learning through large pre-trained models has changed the landscape of current applications in natural language processing (NLP). Recently Optimus, a variational autoencoder (VAE) which combines two pre-trained models, BERT and GPT-2, has been released, and its combination with generative adversarial networks (GANs) has been shown to produce novel, yet very human-looking text. The Optimus and GANs combination avoids the troublesome application of GANs to the discrete domain of text, and prevents the exposure bias of standard maximum likelihood methods. We combine the training of GANs in the latent space, 

Keyword :  Text Generation, Variational Autoencoders, Generative Adversarial Networks, Reinforcement Learning.

For More Details:https://allconferencecfpalerts.com/cfp/view-paper.php?eno=5254

No comments:

Post a Comment