Question Answering On Fairytaleqa
Métriques
F1
Rouge-L
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | F1 | Rouge-L | Paper Title | Repository |
|---|---|---|---|---|
| BART | 0.088 | 0.108 | Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension | |
| BART fine-tuned on FairytaleQA | 0.536 | 0.533 | Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension | |
| DistilBERT | 0.082 | 0.097 | Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension | |
| BART fine-tuned on NarrativeQA | 0.492 | 0.475 | Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension |
0 of 4 row(s) selected.