2017 BagofTricksforEfficientTextClas

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Text Representation System; fastText; Text Classification System

Notes

Cited By

Quotes

Abstract

This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train fastText on more than one billion words in less than ten minutes using a standard multicore CPU, and classify half a million sentences among 312K classes in less than a minute.

References

BibTeX

@inproceedings{2017_BagofTricksforEfficientTextClas,
  author    = {Armand Joulin and
               Edouard Grave and
               Piotr Bojanowski and
               Tomas Mikolov},
  editor    = {Mirella Lapata and
               Phil Blunsom and
               Alexander Koller},
  title     = {Bag of Tricks for Efficient Text Classification},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the
               Association for Computational Linguistics (EACL2017) Volume 2: Short Papers},
  pages     = {427--431},
  publisher = {Association for Computational Linguistics},
  year      = {2017},
  url       = {https://doi.org/10.18653/v1/e17-2068},
  doi       = {10.18653/v1/e17-2068},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2017 BagofTricksforEfficientTextClasTomáš Mikolov
Piotr Bojanowski
Edouard Grave
Armand Joulin
Bag of Tricks for Efficient Text Classification2017