Table 9 Performance with different baseline methods associated with a reference model.

From: An efficient learning based approach for automatic record deduplication with benchmark datasets

Dataset

F1-score

avg

Avg-t

lstm

Lstm-t

Amazon-google

0.66

0.86

0.81

0.823

Amazon-Walmart

0.84

0.875

0.855

0.82

dblp-scholar

0.96

0.965

0.975

0.98

Back to article page