"The tokens correspond to common Hindi grammatical particles and suffixes, such as case markers and postpositions (e.g., \"के\", \"की\", \"का\", \"को\", \"कि\", \"कीya\"), which are essential for indicating relationships between nouns, possession, and grammatical roles in sentences."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.68 | 0.95 | 0.38 | 0.543 | 0.38 | 0.98 | 0.02 | 0.62 |
fuzz | 0.71 | 0.957 | 0.44 | 0.603 | 0.44 | 0.98 | 0.02 | 0.56 |