Coherence Evaluation On Gcdc Rst F1
Metrics
Average F1
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Average F1 |
|---|---|
| discourse-coherence-in-the-wild-a-dataset | 46.65 |
| neural-rst-based-evaluation-of-discourse | 46.98 |
| neural-rst-based-evaluation-of-discourse | 44.30 |