Grammatical Error Detection On Conll 2014 A1
評価指標
F0.5
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | F0.5 |
|---|---|
| jointly-learning-to-label-sentences-and | 22.14 |
| auxiliary-objectives-for-neural-error | 36.1 |
| artificial-error-generation-with-machine | 21.87 |
| semi-supervised-multitask-learning-for | 17.86 |
| compositional-sequence-labeling-models-for | 34.3 |
| compositional-sequence-labeling-models-for | 16.4 |
| auxiliary-objectives-for-neural-error | 17.5 |
| neural-quality-estimation-with-multiple | 54.3 |