Условный ВАЭ

AbstractVariational Autoencoder (VAE) is widely used as a generative model to approximate a model’s posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when …...

AbstractWe introduce CGA, a conditional VAE architecture, to control, generate, and augment text. CGA is able to generate natural English sentences controlling multiple semantic and syntactic attributes by combining adversarial …...

AbstractIn recent years, data augmentation has become an important field of machine learning. While images can use simple techniques such as cropping or rotating, textual data augmentation needs more complex …...