Generating text via adversarial training

Y Zhang, Z Gan, L Carin

Research output: Contribution to journalArticlepeer-review


Abstract Generative Adversarial Networks (GANs) have achieved great success in generating realistic synthetic real-valued data. However, the discrete output of language model hinders the application of gradient-based GANs. In this paper we propose a generic …
Original languageUndefined/Unknown
JournalNIPS workshop on Adversarial Training
StatePublished - 2016
Externally publishedYes

Bibliographical note

Query date: 2021-03-11 11:12:31

Cite this