Blocking On Amazon Google
평가 지표
Candidate Set Size
Recall
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Candidate Set Size | Recall | Paper Title | Repository |
|---|---|---|---|---|
| Sparkly k=50 | 165900 | 99.2 | Sparkly: A Simple yet Surprisingly Strong TF/IDF Blocker for Entity Matching | |
| Auto | 68200 | 97.1 | Deep learning for blocking in entity matching: a design space exploration | |
| SC-Block | 11000 | 99.6 | SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines | - |
| Sudowoodo | 48390 | 97.3 | Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation | - |
| Sparkly k=10 | 33300 | 96.8 | Sparkly: A Simple yet Surprisingly Strong TF/IDF Blocker for Entity Matching | |
| BM25 | 40000 | 98.7 | SC-Block: Supervised Contrastive Blocking within Entity Resolution Pipelines | - |
0 of 6 row(s) selected.