SEQUENTIAL NEURAL TEXT COMPRESSION

The purpose of this paper is to show that neural networks may be promi sing tools for data compression without loss of information, We combin e predictive neural nets and statistical coding techniques to compress tent files. We apply our methods to certain short newspaper articles and obtain compression ratios exceeding those of the widely used Lempe l-Ziv algorithms (which build the basis of the UNIX functions ''compre ss'' and ''gzip''). The main disadvantage of our methods is that they are about three orders of magnitude slower than standard methods.