Table 7 Comparison of various models’ performance on non-word error correction task
From: Improving the quality of Persian clinical text with a novel spelling correction system
\(\mathbf{M}\mathbf{o}\mathbf{d}\mathbf{e}\mathbf{l}\) | Precision | Recall | F1-Score |
|---|---|---|---|
Pre-trained Model | 88.2 | 89.6 | 88.9 |
Pre-trained Model + PERTO | 89.3 | 90.7 | 90.0 |
Yazdani, et al. 2020 [57] | 73.8 | 75.4 | 74.6 |
Continuous Bag-of-Words (CBOW) | 78.7 | 80.8 | 79.7 |