Event Extraction On Ace2005
評価指標
Argument Cl
Trigger Cl
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
モデル名 | Argument Cl | Trigger Cl | Paper Title | Repository |
|---|---|---|---|---|
| Text2Event - T5-large | 53.8 | 71.9 | Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction | |
| DeepStruct multi-task | 63.9 | 69.2 | DeepStruct: Pretraining of Language Models for Structure Prediction | |
| DeepStruct multi-task w/ finetune | 56.2 | 69.8 | DeepStruct: Pretraining of Language Models for Structure Prediction | |
| Text2Event - T5-base | 49.8 | 69.2 | Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction |
0 of 4 row(s) selected.