Table 8 Performance with different similarities.
From: An efficient learning based approach for automatic record deduplication with benchmark datasets
Dataset | F1-score | |||||
|---|---|---|---|---|---|---|
avg | Avg-allsim | lstm | Lstm- allsim | Allcomp- allsim | Allcomp- allsim-t | |
Amazon-google | 0.66 | 0.71 | 0.81 | 0.7725 | 0.78 | 0.80 |
Amazon-Walmart dataset | 0.84 | 0.83 | 0.86 | 0.869 | 0.87 | 0.869 |
dblp-scholar | 0.96 | 0.965 | 0.967 | 0.969 | 0.97 | 0.975 |
