"The highlighted tokens are morphemes, syllables, or word fragments from various languages, often appearing in proper nouns, technical terms, or culturally significant words, especially those related to Indic languages, Sanskrit, and related terminology. These fragments frequently occur at word boundaries or within compound words, reflecting their importance in identifying or constructing key terms across multilingual contexts."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.85 | 0.927 | 0.76 | 0.835 | 0.76 | 0.94 | 0.06 | 0.24 |
fuzz | 0.7 | 0.632 | 0.96 | 0.762 | 0.96 | 0.44 | 0.56 | 0.04 |