Question Answering on XQuAD languages not in MLQA
81.9F1 (el)XLM-R Base MS, LT-SFT
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| XLM-R Base MS, LT-SFTBackbone=XLM-R Base, Fine-tuning Method=Lottery-Ticket Sparse Fine-Tuning (LT-SFT), Training Strategy=Multi-source2021.10 | 81.9 | 65.5 | 86.3 | 73.3 | 81.4 | 64.6 | 82.4 | 75.2 | 75.2 | 58.6 | |
| XLM-R Large, full FTBackbone=XLM-R Large, Fine-tuning Method=Full Fine-Tuning, Training Strategy=Single-source2021.10 | 79.8 | 61.7 | 83.6 | 69.7 | 80.1 | 64.3 | 74.2 | 62.8 | 75.9 | 59.3 | |
| XLM-R Base, full FTBackbone=XLM-R Base, Fine-tuning Method=Full Fine-Tuning, Training Strategy=Single-source2021.10 | 71.1 | 54.3 | 78.3 | 63.7 | 74.1 | 57.8 | 67.1 | 55.7 | 67.5 | 51.1 |