Grammar-based Neural Text-to-SQL Generation

05/30/2019
by   Kevin Lin, et al.
0

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. Grammar-based decoding has shown significant improvements for other semantic parsing tasks, but SQL and other general programming languages have complexities not present in logical formalisms that make writing hierarchical grammars difficult. We introduce techniques to handle these complexities, showing how to construct a schema-dependent grammar with minimal over-generation. We analyze these techniques on ATIS and Spider, two challenging text-to-SQL datasets, demonstrating that they yield 14--18% relative reductions in error.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/26/2022

Faster and Better Grammar-based Text-to-SQL Parsing via Clause-level Parallel Decoding and Alignment Loss

Grammar-based parsers have achieved high performance in the cross-domain...
research
09/21/2022

T5QL: Taming language models for SQL generation

Automatic SQL generation has been an active research area, aiming at str...
research
06/06/2023

DashQL – Complete Analysis Workflows with SQL

We present DashQL, a language that describes complete analysis workflows...
research
05/17/2021

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising

In text-to-SQL task, seq-to-seq models often lead to sub-optimal perform...
research
11/11/2020

IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation

Context-dependent text-to-SQL task has drawn much attention in recent ye...
research
05/23/2023

Flexible Grammar-Based Constrained Decoding for Language Models

LLMs have shown impressive few-shot performance across many tasks. Howev...
research
01/25/2021

GP: Context-free Grammar Pre-training for Text-to-SQL Parsers

A new method for Text-to-SQL parsing, Grammar Pre-training (GP), is prop...

Please sign up or login with your details

Forgot password? Click here to reset