Thai Word Tokenization On Best 2010
评估指标
F1-Score
评测结果
各个模型在此基准测试上的表现结果
模型名称 | 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.