Table 11 Cross-validation performance fluctuations (Unit: %).
Fold Number | Grammar F1 | Vocabulary Suggestion Acceptance Rate | Coherence Score |
|---|---|---|---|
Fold 1 | 88.7 | 71.3 | 4.1 |
Fold 2 | 89.2 | 70.8 | 4.0 |
Fold 3 | 88.5 | 72.1 | 4.2 |
Fold 4 | 89.0 | 71.6 | 4.1 |
Fold 5 | 88.9 | 70.9 | 4.0 |
Mean ± Std Dev | 88.9 ± 0.3 | 71.3 ± 0.6 | 4.1 ± 0.08 |