AI summary

This paper introduces a neural text compression method combining predictive neural networks and statistical coding techniques, surpassing Lempel-Ziv algorithms on newspaper articles, but with significantly slower processing speed, demonstrating the potential of neural networks in data compression.

Abstract

The purpose of this paper is to show that neural networks are promising tools for data compression without loss of information. We combine predictive neural nets and statistical coding techniques to compress text files. We apply our methods to short newspaper articles and obtain compression ratios exceeding those of widely used Lempel-Ziv algorithms (which build the basis of the UNIX functions "compress" and "gzip"). The main disadvantage of our methods is that they are three orders of magnitude slower than standard methods.