Deep Entity Matching with Pre-Trained Language Models
Summary: Ditto casts entity matching as sequence-pair classification and fine-tunes pre-trained Transformers, surpassing prior SOTA by up to 29 F1 points. Domain highlighting, summarization, and hard-example augmentation further improve accuracy while reducing label needs. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yuliang Li (Megagon Labs)
- 2. Jinfeng Li (Megagon Labs)
- 3. Yoshihiko Suhara (Megagon Labs)
- 4. AnHai Doan (University of Wisconsin)
- 5. Wang-Chiew Tan (Megagon Labs)
BibTeX Citation
@article{li_vldb21,
title = {{Deep Entity Matching with Pre-Trained Language Models}},
author = {Li, Yuliang and Li, Jinfeng and Suhara, Yoshihiko and Doan, AnHai and Tan, Wang-Chiew},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {1},
pages = {50--60},
doi = {10.14778/3421424.3421431},
url = {https://doi.org/10.14778/3421424.3421431},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 50 of 94 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 176 | Deep Learning for Entity Matching: A Design Space Exploration | 2018 | SIGMOD | 0.00027191081 |
| 196 | CrowdER: Crowdsourcing Entity Resolution | 2012 | VLDB | 0.00025780596 |
| 248 | Evaluation of entity resolution approaches on real-world match problems | 2010 | VLDB | 0.00023278354 |
| 265 | Human-powered Sorts and Joins | 2012 | VLDB | 0.00022935368 |
| 439 | Corleone: Hands-Off Crowdsourcing for Entity Matching | 2014 | SIGMOD | 0.00018464913 |
| 489 | Distributed Representations of Tuples for Entity Resolution | 2018 | VLDB | 0.0001761456 |
| 529 | Magellan: Toward Building Entity Matching Management Systems | 2016 | VLDB | 0.00017096361 |
| 1,248 | Entity Matching: How Similar Is Similar | 2011 | VLDB | 0.00011498301 |
| 1,465 | Synthesizing Entity Matching Rules by Examples | 2018 | VLDB | 0.00010689571 |
| 2,463 | A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching | 2020 | SIGMOD | 8.5486912e-05 |
| 3,611 | NADEEF/ER: Generic and Interactive Entity Resolution | 2014 | SIGMOD | 7.2580469e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,463 | A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching | 2020 | SIGMOD |
| 2 | 3,446 | Efficient Approximate Entity Extraction with Edit Distance Constraints | 2009 | SIGMOD |
| 3 | 9,610 | The Battleship Approach to the Low Resource Entity Matching Problem | 2023 | SIGMOD |
| 4 | 2,475 | Deep Learning for Blocking in Entity Matching: A Design Space Exploration | 2021 | VLDB |
| 5 | 5,730 | Domain Adaptation for Deep Entity Resolution | 2022 | SIGMOD |
| 6 | 6,192 | Pre-trained Embeddings for Entity Resolution: An Experimental Analysis | 2023 | VLDB |
| 7 | 4,590 | Entity Resolution with Hierarchical Graph Attention Networks | 2022 | SIGMOD |
| 8 | 5,606 | Analyzing How BERT Performs Entity Matching | 2022 | VLDB |
| 9 | 176 | Deep Learning for Entity Matching: A Design Space Exploration | 2018 | SIGMOD |
| 10 | 4,447 | Dual-Objective Fine-Tuning of BERT for Entity Matching | 2021 | VLDB |