Open Information Extraction On Penn Treebank
Metrics
F1
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| DeepEx (zero-shot) | 88.5 | Zero-Shot Information Extraction as a Unified Text-to-Triple Translation |
| DeepStruct multi-task | 54.5 | DeepStruct: Pretraining of Language Models for Structure Prediction |
| Deepstruct zero-shot | 51 | DeepStruct: Pretraining of Language Models for Structure Prediction |
| DeepStruct multi-task w/ finetune | 45,1 | DeepStruct: Pretraining of Language Models for Structure Prediction |
0 of 4 row(s) selected.