# From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing

## TL;DR

This paper explores whether data compression algorithms can match or outperform recurrent neural networks in natural language processing, highlighting fundamental differences between the two approaches and their predictive capabilities.

## Contribution

The paper investigates the potential of data compression algorithms to serve as an alternative to recurrent neural networks in NLP tasks, revealing key differences in their predictive mechanisms.

## Key findings

- Data compression algorithms can perform comparably to RNNs in certain NLP tasks.
- Fundamental differences exist between data compression and neural network prediction methods.
- The study provides insights into the intelligence levels of compression algorithms versus neural networks.

## Abstract

In recent studies [1][13][12] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on predictions. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in natural language processing tasks. If this is possible,then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in specific tasks related to human language. In our journey we discovered what we think is the fundamental difference between a Data Compression Algorithm and a Recurrent Neural Network.