做无监督,关键是找到输出的标签。在NLP中,可以用win1作为输入,邻近的短语win2作为输出,来训练unsupervised deep representation
参考文献:Rie Johnson and Tong Zhang. 2015b. Semi-supervised
convolutional neural networks for text categorization
via region embedding. In Advances in Neural
Information Processing Systems 28 (NIPS 2015).
Deep Pyramid Convolutional Neural Networks for Text Categorization,2016