Part-of-Speech Tagging on Turkish POS Datasets (2 datasets average)
92.1POS AccuracyMursit-Large
Evaluation results
| Method | Links | |
|---|---|---|
| Mursit-LargeModel Type=Post-Trained, Task Context=Non-Retrieval2026.01 | 92.1 | |
| Mursit-BaseModel Type=Post-Trained, Task Context=Non-Retrieval2026.01 | 91.3 | |
| TabiBERTModel Type=Baseline, Task Context=Non-Retrieval2026.01 | 91 |