Bag of Tricks for Efficient Text Classification

EACL 2017 Armand JoulinEdouard GravePiotr BojanowskiTomas Mikolov

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... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Text Classification AG News fastText Error 7.5 # 9
Sentiment Analysis Amazon Review Full FastText Accuracy 60.2 # 5
Sentiment Analysis Amazon Review Polarity FastText Accuracy 94.6 # 5
Text Classification DBpedia FastText Error 1.4 # 12
Sentiment Analysis Sogou News fastText Accuracy 96.8 # 1
Text Classification Yahoo! Answers FastText Accuracy 72.3 # 5
Sentiment Analysis Yelp Binary classification FastText Error 4.3 # 10
Sentiment Analysis Yelp Fine-grained classification FastText Error 36.1 # 8