DeepJoin: Joinable Table Discovery with Pre-trained Language Models
Summary: DeepJoin uses a fine-tuned pre-trained language model to embed textual columns, unifying equi- and semantic join discovery. Fixed-length embeddings enable sublinear ANN retrieval, delivering higher precision and up to 100× speedups. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yuyang Dong (NEC Corporation)
- 2. Chuan Xiao (Nagoya University; Osaka University)
- 3. Takuma Nozawa (NEC Corporation)
- 4. Masafumi Enomoto (NEC Corporation)
- 5. Masafumi Oyamada (NEC Corporation)
BibTeX Citation
@article{dong_vldb23,
title = {{DeepJoin: Joinable Table Discovery with Pre-trained Language Models}},
author = {Dong, Yuyang and Xiao, Chuan and Nozawa, Takuma and Enomoto, Masafumi and Oyamada, Masafumi},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {10},
pages = {2458--2470},
doi = {10.14778/3603581.3603587},
url = {https://doi.org/10.14778/3603581.3603587},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 19 of 19 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 22 of 22 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
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,256 | Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index | 2025 | VLDB |
| 2 | 9,244 | Making Table Understanding Work in Practice | 2022 | CIDR |
| 3 | 1,852 | Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning | 2023 | VLDB |
| 4 | 10,837 | EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries | 2026 | VLDB |
| 5 | 10,673 | Qualitative Join Discovery in Data Lakes using Examples | 2026 | SIGMOD |
| 6 | 10,894 | MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery | 2026 | VLDB |
| 7 | 1,391 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |
| 8 | 8,408 | Fast Approximate Similarity Join in Vector Databases | 2025 | SIGMOD |
| 9 | 10,845 | Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees | 2026 | VLDB |
| 10 | 5,687 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |