Question Answering On Torque
Metriken
C
EM
F1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | C | EM | F1 | Paper Title | Repository |
|---|---|---|---|---|---|
| RoBERTa-large | 34.5 | 51.1 | 75.2 | TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions | - |
| ECONET | 37.0 | 52.0 | 76.3 | ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning |
0 of 2 row(s) selected.