From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
This addresses the problem of understanding and comparing computational intelligence methods for language processing, but it appears incremental as it builds on prior studies without presenting new experimental results.
The paper investigates whether data compression algorithms can match or exceed the performance of recurrent neural networks in natural language processing tasks, concluding that there is a fundamental difference between the two approaches.
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.