2 papers
cs.LG2017
A Self-Training Method for Semi-Supervised GANs
Alan Do-Omri, Dalei Wu, Xiaohua Liu
Since the creation of Generative Adversarial Networks (GANs), much work has been done to improve their training stability, their generated image quality, their range of application…
cs.CL2017
Chunk-Based Bi-Scale Decoder for Neural Machine Translation
Hao Zhou, Zhaopeng Tu, Shujian Huang +3
In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we pr…