论文标题
通过功能匹配学习隐式文本生成
Learning Implicit Text Generation via Feature Matching
论文作者
论文摘要
生成功能匹配网络（GFMN）是一种通过对预训练的神经网络的特征进行匹配来训练图像的隐式生成模型的方法。在本文中，我们提出了有效数据的新GFMN公式。我们的实验结果表明了所提出的方法SEQGFMN的有效性，用于英语中的三个不同的一代任务：无条件的文本生成，课堂条件文本生成和无监督的文本样式转移。 SEQGFMN稳定训练和胜过各种对抗性方法，用于文本和文本样式转移。
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.
