DBScholar

Back to papers

Pre-trained Embeddings for Entity Resolution: An Experimental Analysis

Summary: Thorough empirical study of 12 pre-trained embeddings (fastText, BERT variants) on 17 ER benchmarks, measuring vectorization cost, blocking scalability vs a SOTA deep blocker, and supervised/unsupervised matching performance. Provides actionable insights on encoding vs accuracy trade-offs. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13261
Venue
VLDB
Year
2023
Pagerank
5.947284e-05
Overall Rank
6,192 | 57.52%
DOI
10.14778/3598581.3598594

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{zeakis_vldb23,
        title = {{Pre-trained Embeddings for Entity Resolution: An Experimental Analysis}},
        author = {Zeakis, Alexandros and Papadakis, George and Skoutas, Dimitrios and Koubarakis, Manolis},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {9},
        pages = {2225--2238},
        doi = {10.14778/3598581.3598594},
        url = {https://doi.org/10.14778/3598581.3598594},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 6 of 6 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 13 of 13 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