GPT-2 as a Compression Preprocessor: Improving Gzip for Structured Text Domains

TL;DR

This paper introduces a GPT-2 based preprocessing step to enhance gzip compression efficiency for structured, domain-specific text files like logs and HTML by transforming data into a more compressible form.

Contribution

The paper presents a novel GPT-2 based preprocessing pipeline that improves gzip compression rates for structured domain-specific files, addressing limitations of traditional pattern-based compressors.

Findings

Improved compression of defense logs by 0.34%

Enhanced HTML file compression by 5.8%

Demonstrated effectiveness on real-world and synthetic data

Abstract

In the modern era, large volumes of data are being produced continuously, especially in domain-specific fields such as medical records and clinical files, defence logs and HTML-based web traffic. Data with such volume and complexity needs to be compressed before storing and transmitting efficiently. Data compression has gained significant attention from modern researchers, resulting in the development of fast and efficient compression algorithms such as Gzip. However, since gzip works on the principle of repetition of binary patterns, one of the limitations of gzip is that domain-specific formats like JSON, XML, HTML, and log files, while structured, may have semantic repetition but not syntactic repetition, which gzip finds difficult to compress. In this article, we propose a GPT-based preprocessor for such domain-specific files. We propose a pipeline made up of GPT-2 taking domain-specific files as input, which pattern-based compressors like gzip find difficult to work on. The preprocessor results are output in a file that is designed for compressors like gzip. After preprocessing, the gzip works on the other end of the pipeline and compresses the data as usual. We used different types of both real-world and synthetically generated data, such as logs and HTML files, for the experiment of the proposed model. We found promising results and an improvement of the Defence logs by 0.34 per cent and HTML files by 5.8 per cent.