Thai Word Tokenization On Best 2010
평가 지표
F1-Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | F1-Score | Paper Title | Repository |
|---|---|---|---|
| AttaCut-SC | 0.9839 | AttaCut: A Fast and Accurate Neural Thai Word Segmenter | - |
| Multiple Attentions (char-word-cc) | 0.9899 | Character-based Thai Word Segmentation with Multiple Attentions | |
| Stacked Ensemble (CRF) | 0.9812 | Domain Adaptation of Thai Word Segmentation Models using Stacked Ensemble | |
| ThaiLMCut | 0.9878 | ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation | |
| LATTE (Linguistic units, lattices, PTMs, GNNs) | 0.9907 | LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation |
0 of 5 row(s) selected.