"The highlighted tokens are primarily Hindi morphemes, root words, and grammatical particles that are essential for sentence structure and meaning, including common nouns, verbs, pronouns, and connectors, often marking key semantic or syntactic roles within the sentence."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.71 | 0.957 | 0.44 | 0.603 | 0.44 | 0.98 | 0.02 | 0.56 |
fuzz | 0.69 | 0.788 | 0.52 | 0.627 | 0.52 | 0.86 | 0.14 | 0.48 |