"The highlighted tokens are primarily Japanese morphemes, particles, and content words that serve as grammatical markers, connectors, or key semantic units within sentences. They include noun and verb stems, particles indicating case or topic, and common suffixes or endings, often marking boundaries of phrases or important syntactic roles. Some tokens are also punctuation or function words that structure or segment the text."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.8 | 0.969 | 0.62 | 0.756 | 0.62 | 0.98 | 0.02 | 0.38 |
fuzz | 0.7 | 0.75 | 0.6 | 0.667 | 0.6 | 0.8 | 0.2 | 0.4 |