"The highlighted tokens are primarily Vietnamese morphemes, syllables, or word segments, often marking the start, end, or core of words and phrases. They frequently correspond to meaningful units in Vietnamese grammar or vocabulary, such as nouns, verbs, adjectives, or function words, and sometimes appear at points of syntactic or semantic importance within sentences. The activations also include some English morphemes and punctuation, but the dominant pattern is the focus on Vietnamese linguistic units."
Score Type | Accuracy | Precision | Recall | F1 score | TPR | TNR | FPR | FNR |
---|---|---|---|---|---|---|---|---|
detection | 0.64 | 1.0 | 0.28 | 0.438 | 0.28 | 1.0 | 0.0 | 0.72 |
fuzz | 0.7 | 0.955 | 0.42 | 0.583 | 0.42 | 0.98 | 0.02 | 0.58 |