Open Information Extraction On Nyt
评估指标
F1
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 | Paper Title | Repository |
|---|---|---|---|
| DeepStruct multi-task | 43.6 | DeepStruct: Pretraining of Language Models for Structure Prediction | |
| Deepstruct zero-shot | 28.9 | DeepStruct: Pretraining of Language Models for Structure Prediction | |
| DeepStruct multi-task w/ finetune | 45.0 | DeepStruct: Pretraining of Language Models for Structure Prediction | |
| DeepEx (zero-shot) | 85.5 | Zero-Shot Information Extraction as a Unified Text-to-Triple Translation |
0 of 4 row(s) selected.