2 papers
cs.CL2023
Unlocking the Power of GANs in Non-Autoregressive Text Generation
Da Ren, Yi Cai, Qing Li
Generative Adversarial Networks (GANs) have been studied in text generation to tackle the exposure bias problem. Despite their remarkable development, they adopt autoregressive str…
cs.CL2022
InitialGAN: A Language GAN with Completely Random Initialization
Da Ren, Qing Li
Text generative models trained via Maximum Likelihood Estimation (MLE) suffer from the notorious exposure bias problem, and Generative Adversarial Networks (GANs) are shown to have…