We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics ...

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the ...

This repo contains a diagnostic evaluation benchmark toward the robustness of text-to-SQL models, which contains 17 perturbation test sets to measure the robustness of models from different angles. It ...

Why text-to-SQL isn’t a solved problem (yet) for enterprise AI and data. Multiple LLMs could generate SQL from basic natural language queries. So why bother to create yet another text-to-SQL model?

This benchmark is composed of 18 publicly available text-to-SQL datasets, containing natural language questions from more than 12 domains, SQL queries from more than 3.9K patterns, and 29K databases.

Gretel’s synthetic Text-to-SQL dataset outperforms the b-mc2/sql-create-context dataset across various grading criteria, including compliance with SQL standards (+54.6%), ...