Sequence generative adversarial nets with a conditional discriminator

doi:10.1016/j.neucom.2020.10.108

Sequence generative adversarial nets with a conditional discriminator

2021-03-01

8

PRE

AI

DOI：10.1016/j.neucom.2020.10.108

原文链接

原文求助

摘要

En 中文

The success of Generative Adversarial Networks (GANs) in image generation attracts researchers to design sequence GANs in text generation. However, the discriminators of those sequence GANs usually provide only one signal per sequence, which can not reflect detailed information, e.g. whether a token is appropriate in a sequence. In addition, maximum likelihood pre-training is typically used in those models, which is time-consuming and obscures the effects of adversarial training. To cope with these problems, we propose a new sequence GAN that consists of a conditional discriminator and a discriminator-augmented generator. The conditional discriminator provides a sequence with token level signals. The generator is designed to approximate a discriminator-augmented distribution, which avoids pre-training. Experiments show that the conditional discriminator provides more informative guidance, and our model outperforms existing models according to metrics involving both sampling quality and sampling diversity. (C) 2020 Elsevier B.V. All rights reserved.

Keyword:

Text generation

Adversarial neural networks

Natural language processing

Deep learning

Algorithm

Sequence generative adversarial nets with a conditional discriminator

摘要

AI总结

期刊

机构

引用论文