"The highlighted tokens are predominantly morphemes, roots, prefixes, suffixes, or short function words within Russian, Bulgarian, and related Slavic texts. These segments often mark grammatical features, word formation, or serve as connectors, and are frequently found at the beginning, middle, or end of words, reflecting the agglutinative and inflectional nature of these languages."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.91 | 0.918 | 0.9 | 0.909 | 0.9 | 0.92 | 0.08 | 0.1 |
fuzz | 0.83 | 0.8 | 0.88 | 0.838 | 0.88 | 0.78 | 0.22 | 0.12 |