Table 2.
Comparison of best experimental results on BioASQ 6b, 7b and 8b
| Model | 6b Factoid QA | 7b Factoid QA | 8b Factoid QA | ||||||
|---|---|---|---|---|---|---|---|---|---|
| SAcc | LAcc | MRR | SAcc | LAcc | MRR | SAcc | LAcc | MRR | |
| AUTH [29] | 0.2015 | 0.4020 | 0.2713 | 0.2363 | 0.3710 | 0.2898 | 0.1642 | 0.2853 | 0.2105 |
| ZhuLab-Fudan [30] | 0.2387 | 0.3314 | 0.2762 | 0.2765 | 0.3922 | 0.3252 | 0.3509 | 0.5141 | 0.4115 |
| Google [31] | – | – | – | 0.4201 | 0.5822 | 0.4798 | – | – | – |
| BioBERT [11] | 0.4286 | 0.5714 | 0.4841 | 0.4367 | 0.6274 | 0.5115 | – | – | – |
| UNCC [12] | – | – | – | 0.3554 | 0.4922 | 0.4063 | – | – | – |
| Umass [32] | – | – | – | – | – | – | 0.3133 | 0.4798 | 0.3780 |
| KU-DMIS-2020 [14] | 0.4141 | 0.6134 | 0.4805 | 0.4510 | 0.6245 | 0.5163 | 0.3819 | 0.5719 | 0.4593 |
| Our Model | 0.4517 | 0.6294 | 0.5197 | 0.4444 | 0.6419 | 0.5165 | 0.3937 | 0.6098 | 0.4688 |
Bold values represent the highest results