Bag of Tricks for Efficient Text Classification
Armand Joulin
and
Edouard Grave
and
Piotr Bojanowski
and
Tomas Mikolov
arXiv e-Print archive - 2016 via Local arXiv
Keywords:
cs.CL
First published: 2016/07/06 (8 years ago) 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.
