"The highlighted tokens are predominantly Russian morphemes, roots, and suffixes that form or modify nouns and adjectives, often marking case, number, gender, or forming compound words, especially in contexts describing locations, organizations, or abstract concepts."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.7 | 0.955 | 0.42 | 0.583 | 0.42 | 0.98 | 0.02 | 0.58 |
fuzz | 0.71 | 0.818 | 0.54 | 0.651 | 0.54 | 0.88 | 0.12 | 0.46 |