Kernel-Based Generative Adversarial Networks for Weakly Supervised Learning.

In recent years, Deep Learning methods have become very popular in NLP classification tasks, due to their ability to reach high performances by relying on very simple input representations. One of the drawbacks in training deep architectures is the large amount of annotated data required for effective training. One recent promising method to enable semi-supervised learning in deep architectures has been formalized within Semi-Supervised Generative Adversarial Networks (SS-GANs). In this paper, an SS-GAN is shown to be effective in semantic processing tasks operating in low-dimensional embeddings derived by the unsupervised approximation of rich Reproducing Kernel Hilbert Spaces. Preliminary analyses over a sentence classification task show that the proposed Kernel-based GAN achieves promising results when only 1% of labeled examples are used.