Question Answering on BioASQ (SAME_CONCLUSION, ALL_INFO, PERC_IDEAL)
85.71SAME_CONCLUSION ScoreVerifAI (M2)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VerifAI (M2)Input=BioASQ (Gold Standard), Question Type=Factoid, Samples=492026.01 | 85.71 | 59.18 | 74.72 | |
| VerifAI (M2)Input=BioASQ (Gold Standard), Question Type=List, Samples=362026.01 | 83.33 | 44.44 | 80.36 | |
| VerifAI (M2)Input=BioASQ (Gold Standard), Question Type=Yes/No, Samples=512026.01 | 82.35 | 52.94 | 74.43 | |
| VerifAI (M2)Input=our IR, Question Type=Yes/No, Samples=512026.01 | 82.35 | 49.02 | 73.85 | |
| VerifAI (M2)Input=BioASQ (Gold Standard), Question Type=all, Samples=1782026.01 | 81.46 | 50 | 74.57 | |
| VerifAI (M2)Input=BioASQ (Gold Standard), Question Type=Summary, Samples=422026.01 | 73.81 | 40.48 | 69.59 | |
| VerifAI (M2)Input=our IR, Question Type=Factoid, Samples=492026.01 | 73.47 | 46.94 | 72.07 | |
| VerifAI (M2)Input=our IR, Question Type=all, Samples=1782026.01 | 70.79 | 38.2 | 67.62 | |
| VerifAI (M2)Input=our IR, Question Type=Summary, Samples=422026.01 | 69.05 | 28.57 | 64.56 | |
| VerifAI (M2)Input=our IR, Question Type=List, Samples=362026.01 | 52.78 | 22.22 | 57.18 |