Compressing text classification models

Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Herve Jegou, Tomas Mikolov

Nov 04, 2016 (modified: Nov 05, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: 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 the word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent the quantization artifacts. As a result, our approach produces a text classifier, derived from the fastText approach, which at test time requires only a fraction of the memory compared to the original one, without noticeably sacrificing the quality in terms of classification accuracy. 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.
  • TL;DR: Compressing text classification models
  • Conflicts:,,,
  • Keywords: Natural language processing, Supervised Learning, Applications