This repository contains the data generation pipeline for our end-to-end NL-to-SQL translation system DBPal.
If you use this work in any way for academic/scientific purpose, please cite our SIGMOD 2020 paper:
@inproceedings{weir2020dbpal,
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 H{\"a}ttasch, Benjamin and Eger, Steffen and others},
booktitle={Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data},
pages={2347--2361},
year={2020}
}
This repository is separated into a source code directory and a documentation directory. For setup instructions etc. please refer to the documentation.
DBPal: A Fully Pluggable NL2SQL Training Pipeline N Weir, P Utama, A Galakatos, A Crotty, A Ilkhechi, S Ramaswamy, ... Proceedings of the 2020 ACM SIGMOD International Conference on Management of …
DBPal: Weak Supervision for Learning a Natural Language Interface to Databases N Weir, A Crotty, A Galakatos, A Ilkhechi, S Ramaswamy, R Bhushan, ... arXiv preprint arXiv:1909.06182
Dbpal: A learned nl-interface for databases F Basik, B Hättasch, A Ilkhechi, A Usta, S Ramaswamy, P Utama, N Weir, ... Proceedings of the 2018 International Conference on Management of Data, 1765 …
An end-to-end neural natural language interface for databases P Utama, N Weir, F Basik, C Binnig, U Çetintemel, B Hättasch, A Ilkhechi, ... arXiv preprint arXiv:1804.00401