DocuT5: Seq2seq SQL Generation with Table Documentation

TL;DR

DocuT5 enhances SQL generation by integrating table documentation and structure knowledge into a seq2seq model, significantly improving accuracy on complex, cross-domain, multi-table questions.

Contribution

It introduces DocuT5, a novel approach that injects external documentation and table structure knowledge into a T5-based model for better domain generalization in SQL generation.

Findings

Reduced foreign key errors to 19.6%.

Improved accuracy on Spider datasets.

Achieved state-of-the-art results with domain knowledge.

Abstract

Current SQL generators based on pre-trained language models struggle to answer complex questions requiring domain context or understanding fine-grained table structure. Humans would deal with these unknowns by reasoning over the documentation of the tables. Based on this hypothesis, we propose DocuT5, which uses off-the-shelf language model architecture and injects knowledge from external `documentation' to improve domain generalization. We perform experiments on the Spider family of datasets that contain complex questions that are cross-domain and multi-table. Specifically, we develop a new text-to-SQL failure taxonomy and find that 19.6% of errors are due to foreign key mistakes, and 49.2% are due to a lack of domain knowledge. We proposed DocuT5, a method that captures knowledge from (1) table structure context of foreign keys and (2) domain knowledge through contextualizing tables and columns. Both types of knowledge improve over state-of-the-art T5 with constrained decoding on Spider, and domain knowledge produces state-of-the-art comparable effectiveness on Spider-DK and Spider-SYN datasets.