DBScholar

Back to papers

DBPal: A Fully Pluggable NL2SQL Training Pipeline

Summary: DBPal proposes a pluggable NL2SQL pipeline that automatically generates synthetic data to augment existing NL2SQL models. It improves translation accuracy and robustness, with DB-specific specialization, reducing reliance on costly labeled data. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
5864
Venue
SIGMOD
Year
2020
Pagerank
9.2060425e-05
Overall Rank
2,079 | 85.74%
DOI
10.1145/3318464.3380589

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{weir_sigmod20,
        title = {{DBPal: A Fully Pluggable NL2SQL Training Pipeline}},
        author = {Weir, Nathaniel and Utama, Prasetya and Galakatos, Alex and Crotty, Andrew and Ilkhechi, Amir and Ramaswamy, Shekar and Bhushan, Rohin and Geisler, Nadja and Hättasch, Benjamin and Eger, Steffen and Cetintemel, Ugur and Binnig, Carsten},
        series = {{SIGMOD} '20},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3318464.3380589},
        url = {https://dl.acm.org/doi/10.1145/3318464.3380589},
        year = {2020}
}

Incoming Citations (Sorted by Pagerank)

Showing 11 of 11 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