Dataset | P (%) | R (%) | F (%) | Dataset | P (%) | R (%) | F (%) |
---|
CDR | 91.42 | 83.59 | 87.86 | CDR | 91.42 | 83.59 | 87.86 |
CDR + CDWC | 90.17 | 84.49 | 87.24 | CDR + CDWA | 94.02 | 71.02 | 80.92 |
CDWC | 89.72 | 83.65 | 86.58 | CDWA | 94.75 | 67.27 | 78.68 |
CDWC1 | 89.84 | 89.32 | 89.58 | CDWA1 | 90.16 | 88.94 | 89.55 |
CDWC2 | 90.00 | 89.35 | 89.67 | CDWA2 (CDRA) | 91.03 | 88.31 | 89.65 |
CDWC3(CDRC) | 89.80 | 89.82 | 89.81 | CDWA3 | 90.28 | 89.03 | 89.65 |
CDWC4 | 89.90 | 89.70 | 89.80 | Â | Â | Â | Â |
- The highest scores are highlighted in bold
- All results are evaluated on the CDR test set. The first two lines are the baselines. For the last 5 lines, each dataset is constructed by the correction model trained with the dataset right above it. The superscript represents the re-correction times. That is, CDWC1 is the dataset constructed by the correction model trained on the CDWC. The third row datasets are the weakly labeled datasets without re-correction. What’s more, CDWC3 is CDRC, and CDWA2 is CDRA