Corpus ID: 173188416

Grammar-based Neural Text-to-SQL Generation

@article{Lin2019GrammarbasedNT,
  title={Grammar-based Neural Text-to-SQL Generation},
  author={Kevin Lin and Ben Bogin and Mark Neumann and Jonathan Berant and Matt Gardner},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.13326}
}
  • Kevin Lin, Ben Bogin, +2 authors Matt Gardner
  • Published in ArXiv 2019
  • Computer Science
  • The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. [...] Key Result We analyze these techniques on ATIS and Spider, two challenging text-to-SQL datasets, demonstrating that they yield 14--18\% relative reductions in error.Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-5 OF 5 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    Long Short-Term Memory

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL