kNN using a gzip-based distance metric outperforms BERT and other neural methods for OOD sentence classification
kNN using a gzip-based distance metric outperforms BERT and other neural methods for OOD sentence classification
![the background blur](https://lemmy.world/pictrs/image/39b0a7c4-23bc-4542-88b4-91dd1f0d2ca1.jpeg?thumbnail=256&format=webp)
![](https://lemmy.world/pictrs/image/39b0a7c4-23bc-4542-88b4-91dd1f0d2ca1.jpeg?thumbnail=1024&format=webp)
intuition: 2 texts similar if cat-ing one to the other barely increases gzip size
no training, no tuning, no params — this is the entire algorithm
0
comments