# Deep Neural Networks for Czech Multi-label Document Classification

## TL;DR

This paper explores deep neural networks for Czech multi-label document classification, demonstrating that simple feature-based models outperform traditional methods, with convolutional networks achieving the best results.

## Contribution

It introduces the use of deep neural networks, specifically CNNs, for Czech document classification without complex pre-processing, outperforming traditional feature-based methods.

## Key findings

- Deep neural networks outperform baseline methods.
- Convolutional networks achieve the best accuracy.
- Simple features suffice for effective classification.

## Abstract

This paper is focused on automatic multi-label document classification of Czech text documents. The current approaches usually use some pre-processing which can have negative impact (loss of information, additional implementation work, etc). Therefore, we would like to omit it and use deep neural networks that learn from simple features. This choice was motivated by their successful usage in many other machine learning fields. Two different networks are compared: the first one is a standard multi-layer perceptron, while the second one is a popular convolutional network. The experiments on a Czech newspaper corpus show that both networks significantly outperform baseline method which uses a rich set of features with maximum entropy classifier. We have also shown that convolutional network gives the best results.