Question Answering On Muld Hotpotqa
Metriken
BLEU-1
BLEU-4
METEOR
Rouge-L
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | BLEU-1 | BLEU-4 | METEOR | Rouge-L | Paper Title | Repository |
---|---|---|---|---|---|---|
Longformer | 30.38 | 16.76 | 4.98 | 30.49 | MuLD: The Multitask Long Document Benchmark | |
T5 | 28.11 | 13.63 | 4.46 | 27.61 | MuLD: The Multitask Long Document Benchmark |
0 of 2 row(s) selected.