“Less Is More: Parameter-Free Text Classification With Gzip”, Zhiying Jiang, Matthew Y. R. Yang, Mikhail Tsirlin, Raphael Tang, Jimmy Lin2022-12-19 (retrieval AI, Transformer, compression; backlinks)⁠:

[buggy? deeply misleading?] Deep neural networks (DNNs) are often used for text classification tasks as they usually achieve high levels of accuracy. However, DNNs can be computationally intensive with billions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize and to transfer to out-of-distribution (OOD) cases in practice.

In this paper, we propose a non-parametric alternative to DNNs that’s easy, light-weight and universal in text classification: a combination of a simple compressor like gzip with a k-nearest-neighbor classifier.

Without any training, pre-training or fine-tuning, our method achieves results that are competitive with non-pretrained deep learning methods on 6 in-distributed datasets. It even outperforms BERT on all 5 OOD datasets, including 4 low-resource languages.

Our method also performs particularly well in few-shot settings where labeled data are too scarce for DNNs to achieve a satisfying accuracy.

[Like all “stupid compressor tricks”, this will be more amusing & overhyped than useful or relevant long-term. cf. N-Grammer, Copy is all You Need]

Backlinks: