Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks. In this paper, we present new GFMN formulations that are effective for sequential data. Our experimental results show the effectiveness of the proposed method, SeqGFMN, for three distinct generation tasks in English: unconditional text generation, class-conditional text generation, and unsupervised text style transfer. SeqGFMN is stable to train and outperforms various adversarial approaches for text generation and text style transfer.
@article{arxiv.2005.03588,
title = {Learning Implicit Text Generation via Feature Matching},
author = {Inkit Padhi and Pierre Dognin and Ke Bai and Cicero Nogueira dos Santos and Vijil Chenthamarakshan and Youssef Mroueh and Payel Das},
journal= {arXiv preprint arXiv:2005.03588},
year = {2020}
}