"The highlighted tokens are primarily function words, grammatical particles, and common morphemes from multiple languages, including Vietnamese, Thai, Hindi, Russian, French, and Spanish. These tokens often serve as connectors, case markers, prepositions, conjunctions, pronouns, or inflectional endings, and are essential for sentence structure and meaning across diverse linguistic contexts."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.55 | 0.531 | 0.86 | 0.656 | 0.86 | 0.24 | 0.76 | 0.14 |
fuzz | 0.51 | 0.506 | 0.88 | 0.642 | 0.88 | 0.14 | 0.86 | 0.12 |