Bag of Tricks for Efficient Text Classification

Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov
7/6/2016
cs.CL

Official code: facebookresearch/fastText (26,521 stars, MIT, last commit 2024-03-22).

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.

View on arXivView PDF

Code Implementations(1)

facebookresearch/fastTextOfficial100%
MIT

Library for fast text representation and classification.

26,5214,831C++, CSSJul 16, 20162 years agoMIT

Similar Papers

Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation

83% match2024

Text Classification: A Perspective of Deep Learning Methods

83% match2023

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

82% match1 repo2023

EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks

82% match1 repo1.7k2019

Text Classification Algorithms: A Survey

81% match1 repo1.8k2019

Kathleen: Oscillator-Based Byte-Level Text Classification Without Tokenization or Attention

81% match2026

Cite this paper

@article{joulin2016tricks,
  title  = {Bag of Tricks for Efficient Text Classification},
  author = {Armand Joulin and Edouard Grave and Piotr Bojanowski and Tomas Mikolov},
  year   = {2016},
  eprint = {1607.01759},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1607.01759}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1607.01759.svg)](https://codeofpaper.com/paper/1607.01759)

Discussion