Japanese Word Segmentation On Bccwj
Metrics
F1-score (Word)
Results
Performance results of various models on this benchmark
Model Name | F1-score (Word) | Paper Title | Repository |
|---|---|---|---|
| LATTE (Linguistic units, lattices, PTMs, GNNs) | 0.9936 | LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation | |
| Word Attention | 0.9893 | Incorporating Word Attention into Character-Based Word Segmentation | |
| LSTM | 0.9842 | Long Short-Term Memory for Japanese Word Segmentation | - |
0 of 3 row(s) selected.