Compressing text classification models

12 Dec 2016Armand Joulin • Edouard Grave • Piotr Bojanowski • Matthijs Douze • Hérve Jégou • Tomas Mikolov

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.

Full paper


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.