Japanese Word Segmentation On Bccwj
평가 지표
F1-score (Word)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | 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.