Research Article

Natural Language Processing Algorithms for Normalizing Expressions of Synonymous Symptoms in Traditional Chinese Medicine

Table 6

The top 5 and 10 recall on the test set.

ModelHFDSTDS
Top 5 recallTop 10 recallTop 5 recallTop 10 recall

Encoder (Char)-Classification0.9692 ± 0.00280.9818 ± 0.00130.8906 ± 0.00450.9164 ± 0.0037
Encoder (Word)-Classification0.9635 ± 0.00250.9785 ± 0.00150.8928 ± 0.00460.9195 ± 0.0038
BERT-Classification0.9758±0.00120.9858±0.00110.9212±0.00190.9426±0.0015

Note. The results are expressed as mean ± SD. , compared with BERT-Classification.