EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries
Summary: EcoTable performs query-driven lake table integration: natural-language queries guide schema linking, Steiner-tree join discovery, and LLM-generated transformations. A lightweight join graph reduces LLM calls, improving accuracy by over 30% while cutting invocation costs 5×. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yuhui Wang (Beijing Institute of Technology)
- 2. Jinqi Liu (Beijing Institute of Technology)
- 3. Chengliang Chai (Beijing Institute of Technology)
- 4. Hangyu Zhao (Beijing Institute of Technology)
- 5. Yuhao Deng (Beijing Institute of Technology)
- 6. Yuyu Luo (Hong Kong University of Science and Technology)
- 7. Xin Tang (University of Wisconsin)
- 8. Ye Yuan (Beijing Institute of Technology)
- 9. Guoren Wang (Beijing Institute of Technology)
- 10. Fengjin Wang (Kuaishou)
- 11. Lei Cao (Massachusetts Institute of Technology)
BibTeX Citation
@article{wang_vldb26,
title = {{EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries}},
author = {Wang, Yuhui and Liu, Jinqi and Chai, Chengliang and Zhao, Hangyu and Deng, Yuhao and Luo, Yuyu and Tang, Xin and Yuan, Ye and Wang, Guoren and Wang, Fengjin and Cao, Lei},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {2936--2949},
doi = {10.14778/3836663.3836664},
url = {https://doi.org/10.14778/3836663.3836664},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next