FastText.zip: Compressing text classification models
This work addresses memory constraints for deploying text classification models, particularly in resource-limited environments, and is incremental as it builds on existing quantization techniques.
The paper tackles the problem of creating compact text classification models to fit in limited memory by proposing a method based on product quantization for storing word embeddings, which reduces memory usage by two orders of magnitude compared to fastText with only a slight accuracy loss.
We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with respect to accuracy. As a result, it outperforms the state of the art by a good margin in terms of the compromise between memory usage and accuracy.