Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset

Benchmark Model Rank Results
text-classification-on-lot-instsCharacter-BERT+RS#1Accuracy: 83.73Macro-F1: 65.9
text-classification-on-lot-instsCD-V1#2Accuracy: 79.97Macro-F1: 59.64
text-classification-on-lot-instssCool#3Accuracy: 76.72Macro-F1: 52.41
text-classification-on-lot-instsFastText#4Accuracy: 74.93Macro-F1: 44.38
text-classification-on-lot-instsNaive Bayes#5Accuracy: 72.2Macro-F1: 50.2