Table 5 Mean slot \(F_1\) values per template. Each cell shows mean and standard deviation of 10 training runs with the best found hyperparameters for best (w.r.t. validation \(F_1\) score) configurations of each category. Numbers rounded to two decimal places, best values marked bold
| Â | Type 2 diabetes \(F_1\) (\(\pm \sigma\)) | Glaucoma \(F_1\) (\(\pm \sigma\)) | ||
|---|---|---|---|---|
Template name | Generative | Extractive | Generative | Extractive |
Arm | 0.7 (± 0.21) | 0.87 (± 0.02) | 0.34 (± 0.06) | 0.36 (± 0.04) |
ClinicalTrial | 0.62 (± 0.02) | 0.82 (± 0.02) | 0.63 (± 0.03) | 0.78 (± 0.02) |
DiffBetweenGroups | 0.41 (± 0.06) | 0.45 (± 0.03) | 0.28 (± 0.08) | 0.37 (± 0.04) |
Endpoint | 0.39 (± 0.03) | 0.43 (± 0.01) | 0.33 (± 0.04) | 0.42 (± 0.09) |
Intervention | 0.61 (± 0.06) | 0.62 (± 0.02) | 0.26 (± 0.02) | 0.42 (± 0.12) |
Medication | 0.48 (± 0.02) | 0.34 (± 0.02) | 0.62 (± 0.08) | 0.53 (± 0.02) |
Outcome | 0.2 (± 0.03) | 0.11 (± 0.01) | 0.35 (± 0.04) | 0.38 (± 0.01) |
Population | 0.22 (± 0.03) | 0.52 (± 0.07) | 0.56 (± 0.04) | 0.52 (± 0.03) |
Publication | 0.95 (± 0.03) | 0.96 (± 0.01) | 0.86 (± 0.02) | 0.9 (± 0.02) |