Database Paper Browser

Back to papers

Analyzing How BERT Performs Entity Matching

Summary: Multi-facet analysis of BERT-based EM: fine-tuning mainly reshapes the last layers, with different effects on matching vs non-matching tokens. BERT also leverages the pairwise-structured descriptions, while pairwise token similarity is not the core knowledge exploited. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12675
Venue
VLDB
Year
2022
Pagerank
4.9517546e-05
Overall Rank
6,711 | 53.32%
DOI
10.14778/3529337.3529356

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Rank Citing Paper Year Venue Pagerank
3,396 Automatic Data Repair: Are We Ready to Deploy? 2024 VLDB 7.1455126e-05
7,052 Pre-trained Embeddings for Entity Resolution: An Experimental Analysis 2023 VLDB 4.8497453e-05
8,908 Deep Active Alignment of Knowledge Graph Entities and Schemata 2023 SIGMOD 4.427232e-05
10,617 Deduplicated Sampling On-Demand 2025 VLDB 4.1945683e-05
10,835 Large Language Models for Spatial Analysis Queries 2025 VLDB 4.1945683e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers