Cross Lingual Question Answering On Tydiqa
評価指標
EM
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | EM |
|---|---|
| transcending-scaling-laws-with-0-1-extra | 54.6 |
| scaling-instruction-finetuned-language-models | 67.8 |
| rethinking-embedding-coupling-in-pre-trained-1 | 42.8 |
| byt5-towards-a-token-free-future-with-pre | 60.0 |
| byt5-towards-a-token-free-future-with-pre | 81.9 |
| palm-2-technical-report-1 | - |
| scaling-instruction-finetuned-language-models | 68.3 |
| palm-2-technical-report-1 | - |
| transcending-scaling-laws-with-0-1-extra | 78.4 |
| palm-2-technical-report-1 | - |
| palm-scaling-language-modeling-with-pathways-1 | 52.9 |