Debian Codegraph @

docs/supervised-models.md

raw
1 ---
2 id: supervised-models
3 title: Supervised models
4 ---
5
6 This page gathers several pre-trained supervised models on several datasets.
7
8 ### Description
9
10 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.
11
12 ```bash
13 -qnorm -retrain -cutoff 100000
14 ```
15
16 ### Table of models
17
18 Each entry describes the test accuracy and size of the model. You can click on a table cell to download the corresponding model.
19
20 | dataset | ag news | amazon review full | amazon review polarity | dbpedia |
21 |-----------|-----------------------|-----------------------|------------------------|------------------------|
22 | regular | [0.924 / 387MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/ag_news.bin) | [0.603 / 462MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/amazon_review_full.bin) | [0.946 / 471MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/amazon_review_polarity.bin) | [0.986 / 427MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/dbpedia.bin) |
23 | compressed | [0.92 / 1.6MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/ag_news.ftz) | [0.599 / 1.6MB]( https://dl.fbaipublicfiles.com/fasttext/supervised-models/amazon_review_full.ftz) | [0.93 / 1.6MB]( https://dl.fbaipublicfiles.com/fasttext/supervised-models/amazon_review_polarity.ftz) | [0.984 / 1.7MB]( https://dl.fbaipublicfiles.com/fasttext/supervised-models/dbpedia.ftz) |
24
25 | dataset | sogou news | yahoo answers | yelp review polarity | yelp review full |
26 |-----------|----------------------|------------------------|----------------------|------------------------|
27 | regular | [0.969 / 402MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/sogou_news.bin) | [0.724 / 494MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/yahoo_answers.bin)| [0.957 / 409MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/yelp_review_polarity.bin)| [0.639 / 412MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/yelp_review_full.bin)|
28 | compressed | [0.968 / 1.4MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/sogou_news.ftz) | [0.717 / 1.6MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/yahoo_answers.ftz) | [0.957 / 1.5MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/yelp_review_polarity.ftz) | [0.636 / 1.5MB](https://dl.fbaipublicfiles.com/fasttext/supervised-models/yelp_review_full.ftz) |
29
30 ### References
31
32 If you use these models, please cite the following paper:
33
34 [1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, [*Bag of Tricks for Efficient Text Classification*](https://arxiv.org/abs/1607.01759)
35
36 ```markup
37 @article{joulin2016bag,
38 title={Bag of Tricks for Efficient Text Classification},
39 author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas},
40 journal={arXiv preprint arXiv:1607.01759},
41 year={2016}
42 }
43 ```
44
45 [2] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. Jégou, T. Mikolov, [*FastText.zip: Compressing text classification models*](https://arxiv.org/abs/1612.03651)
46
47 ```markup
48 @article{joulin2016fasttext,
49 title={FastText.zip: Compressing text classification models},
50 author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Douze, Matthijs and J{\'e}gou, H{\'e}rve and Mikolov, Tomas},
51 journal={arXiv preprint arXiv:1612.03651},
52 year={2016}
53 }
54 ```