Arabic Text Diacritization On Tashkeela 1
Metrics
Diacritic Error Rate
Word Error Rate (WER)
Results
Performance results of various models on this benchmark
Model Name | Diacritic Error Rate | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|---|
| Shakkelha | 0.0169 | 0.0509 | Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation | |
| CBHG model | 0.0113 | 0.0443 | Effective Deep Learning Models for Automatic Diacritization of Arabic Text | |
| D3 (D2 + decoder) | 0.0183 | 0.0534 | Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization | |
| MC | 0.0339 | 0.0994 | Multi-components System for Automatic Arabic Diacritization | |
| Shakkala | 0.0373 | 0.1119 | Arabic Text Diacritization Using Deep Neural Networks | |
| D2 | 0.0185 | 0.0553 | Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization |
0 of 6 row(s) selected.