Table 7 Results of models with different feature extractor on ChiNesE dataset.
From: Transformer-based prototype network for Chinese nested named entity recognition
Feature Extractor | F1 | ||||
|---|---|---|---|---|---|
BERT | 84.82 | 84.62 | 84.51 | 84.79 | 84.46 |
roberta | 84.2 | 84.19 | 83.92 | 84.01 | 84.22 |
longformer | 84.07 | 83.89 | 84.22 | 83.97 | 84.32 |
roformer | 76.68 | 75.96 | 76.65 | 76.33 | 76.71 |
-BiLSTM | 84.2 | 84.51 | 84.11 | 84.22 | 84.32 |
