Table 10 The average accuracy of the model under different number of industry categorie.

From: Analyzing the capability description of testing institution in Chinese phrase using a joint approach of semi-supervised K-Means clustering and BERT

Number of Classes

Classifications

Average Accuracy

2

Textile products/Information Technology

98.2%

3

Textile products/Information Technology/Medicine and Healthcare

96.10%

4

Textile products/Information Technology/Medicine and Healthcare/Household Goods

92.10%

5

Textile products/Information Technology/Medicine and Healthcare/Household Goods/Agrochemicals

89.80%

Back to article page