Question Answering on BioASQ (dev)
77.8F1 ScoreFewshotQA w/ MINPROMPT
Evaluation results
| Method | Links | |
|---|---|---|
| FewshotQA w/ MINPROMPTNumber of training examples=128, Number of Parameters=406M2023.10 | 77.8 | |
| FewshotQANumber of training examples=128, Number of Parameters=406M2023.10 | 77.2 | |
| PMRNumber of training examples=128, Number of Parameters=406M2023.10 | 76.8 | |
| FewshotQANumber of training examples=64, Number of Parameters=406M2023.10 | 73.2 | |
| FewshotQA w/ MINPROMPTNumber of training examples=64, Number of Parameters=406M2023.10 | 72.4 | |
| PMRNumber of training examples=64, Number of Parameters=406M2023.10 | 68.2 | |
| Splinter w/ MINPROMPTNumber of training examples=128, Number of Parameters=110M2023.10 | 67.8 | |
| FewshotQANumber of training examples=32, Number of Parameters=406M2023.10 | 66.9 | |
| FewshotQA w/ MINPROMPTNumber of training examples=32, Number of Parameters=406M2023.10 | 63.6 | |
| SplinterNumber of training examples=128, Number of Parameters=110M2023.10 | 63.2 | |
| PMRNumber of training examples=32, Number of Parameters=406M2023.10 | 62.9 | |
| FewshotQANumber of training examples=16, Number of Parameters=406M2023.10 | 62.7 | |
| Splinter w/ MINPROMPTNumber of training examples=64, Number of Parameters=110M2023.10 | 59.4 | |
| FewshotQA w/ MINPROMPTNumber of training examples=16, Number of Parameters=406M2023.10 | 57.2 | |
| PMRNumber of training examples=16, Number of Parameters=406M2023.10 | 54.2 | |
| SpanBERTNumber of training examples=128, Number of Parameters=110M2023.10 | 52.2 | |
| Splinter w/ MINPROMPTNumber of training examples=32, Number of Parameters=110M2023.10 | 49.2 | |
| RoBERTaNumber of training examples=128, Number of Parameters=110M2023.10 | 46.1 | |
| SplinterNumber of training examples=64, Number of Parameters=110M2023.10 | 45.4 | |
| Splinter w/ MINPROMPTNumber of training examples=16, Number of Parameters=110M2023.10 | 38.7 | |
| SplinterNumber of training examples=32, Number of Parameters=110M2023.10 | 36.5 | |
| SpanBERTNumber of training examples=64, Number of Parameters=110M2023.10 | 35.3 | |
| RoBERTaNumber of training examples=64, Number of Parameters=110M2023.10 | 34 | |
| SplinterNumber of training examples=16, Number of Parameters=110M2023.10 | 28.2 | |
| SpanBERTNumber of training examples=32, Number of Parameters=110M2023.10 | 25.1 | |
| RoBERTaNumber of training examples=32, Number of Parameters=110M2023.10 | 23.3 | |
| RoBERTaNumber of training examples=16, Number of Parameters=110M2023.10 | 16.7 | |
| SpanBERTNumber of training examples=16, Number of Parameters=110M2023.10 | 15.9 |