"The tokens \"े\" and \"ा\" are highly activated as common Hindi grammatical suffixes, frequently marking case, possession, plurality, or verb forms, and often appear at the end of words or as postpositions."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.79 | 0.939 | 0.62 | 0.747 | 0.62 | 0.96 | 0.04 | 0.38 |
fuzz | 0.78 | 0.938 | 0.6 | 0.732 | 0.6 | 0.96 | 0.04 | 0.4 |