A natural language database interface (NLDB) can democratize data-driven insights for non-technical users. However, existing Text-to-SQL semantic parsers cannot achieve high enough accuracy in the cross-database setting to allow good usability in practice. This work presents Turing, an NLDB system toward bridging this gap. The cross-domain semantic parser of \mname with our novel value prediction method achieves 75.1% execution accuracy, and 78.3% top-5 beam execution accuracy on the Spider validation set (Yu et al., 2018b). To benefit from the higher beam accuracy, we design an interactive system where the SQL hypotheses in the beam are explained step-by-step in natural language, with their differences highlighted. The user can then compare and judge the hypotheses to select which one reflects their intention if any. The English explanations of SQL queries in Turing are produced by our high-precision natural language generation system based on synchronous grammars.

BibTeX

@inproceedings{xu2021turing,
    title = {TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface},
    author = {Peng Xu and Wenjie Zi and Hamidreza Shahidi and {\'A}kos K{\'a}d{\'a}r and Keyi Tang and Wei Yang and Jawad Ateeq and Harsh Barot and Meidan Alon and Yanshuai Cao},
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    month = jul,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
}