Supervised models

This page gathers several pre-trained supervised models on several datasets.

Description

The regular models are trained using the procedure described in [1]. They can be reproduced using the classification-results.sh script within our github repository. The quantized models are build by using the respective supervised settings and adding the following flags to the quantize subcommand.

-qnorm -retrain -cutoff 100000

Table of models

Each entry describes the test accuracy and size of the model. You can click on a table cell to download the corresponding model.

dataset	ag news	amazon review full	amazon review polarity	dbpedia
regular	0.924 / 387MB	0.603 / 462MB	0.946 / 471MB	0.986 / 427MB
compressed	0.92 / 1.6MB	0.599 / 1.6MB	0.93 / 1.6MB	0.984 / 1.7MB

dataset	sogou news	yahoo answers	yelp review polarity	yelp review full
regular	0.969 / 402MB	0.724 / 494MB	0.957 / 409MB	0.639 / 412MB
compressed	0.968 / 1.4MB	0.717 / 1.6MB	0.957 / 1.5MB	0.636 / 1.5MB

References

If you use these models, please cite the following paper:

[1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, Bag of Tricks for Efficient Text Classification

@article{joulin2016bag,
  title={Bag of Tricks for Efficient Text Classification},
  author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas},
  journal={arXiv preprint arXiv:1607.01759},
  year={2016}
}

[2] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. Jégou, T. Mikolov, FastText.zip: Compressing text classification models

@article{joulin2016fasttext,
  title={FastText.zip: Compressing text classification models},
  author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Douze, Matthijs and J{\'e}gou, H{\'e}rve and Mikolov, Tomas},
  journal={arXiv preprint arXiv:1612.03651},
  year={2016}
}