MATEC Web Conf.
Volume 292, 201923rd International Conference on Circuits, Systems, Communications and Computers (CSCC 2019)
|Number of page(s)||9|
|Published online||24 September 2019|
Deep Generative Model with Supervised Latent Space for Text Classification
Faculty of Cybernetics, Military University of Technology in Warsaw
* e-mail: email@example.com
Recent advances in applying deep neural networks to Bayesian Modelling, sparked resurgence of in- terest in Variational Methods. Notably, the main contribution in this area is Reparametrization Trick introduced in  and . VAE model , is unsupervised and therefore its application to classification is not optimal. In this work, we research the possibility to extend the model to supervised case. We first start with the model known as Supervised Variational Autoencoder that is researched in the literature in various forms  and . We then modify objective function in such a way, that latent space can be better fitted to multiclass problem. Finally, we introduce a new method that uses information about classes to modify latent space, so it even better reflects differences between classes. All of this, will use only two dimensions. We will show, that mainstream classifiers applied to such a space, achieve significantly better performance than if applied to original datasets and VAE generated data. We also show, how our novel approach can be used to calculate better classification score, and how it can be used to generate data for a given class.
© The Authors, published by EDP Sciences, 2019
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.