Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation

TL;DR

Metasql is a generate-then-rank framework that enhances natural language to SQL translation by controlling candidate generation with metadata and selecting the best query through learning-to-rank methods, improving accuracy on benchmarks.

Contribution

Introduces a flexible generate-then-rank framework with query metadata and learning-to-rank algorithms to improve NL to SQL translation accuracy.

Findings

Significantly improves translation accuracy on benchmark datasets.

Effectively controls SQL candidate generation with metadata.

Outperforms existing auto-regressive models in NLIDB tasks.

Abstract

The Natural Language Interface to Databases (NLIDB) empowers non-technical users with database access through intuitive natural language (NL) interactions. Advanced approaches, utilizing neural sequence-to-sequence models or large-scale language models, typically employ auto-regressive decoding to generate unique SQL queries sequentially. While these translation models have greatly improved the overall translation accuracy, surpassing 70% on NLIDB benchmarks, the use of auto-regressive decoding to generate single SQL queries may result in sub-optimal outputs, potentially leading to erroneous translations. In this paper, we propose Metasql, a unified generate-then-rank framework that can be flexibly incorporated with existing NLIDBs to consistently improve their translation accuracy. Metasql introduces query metadata to control the generation of better SQL query candidates and uses learning-to-rank algorithms to retrieve globally optimized queries. Specifically, Metasql first breaks down the meaning of the given NL query into a set of possible query metadata, representing the basic concepts of the semantics. These metadata are then used as language constraints to steer the underlying translation model toward generating a set of candidate SQL queries. Finally, Metasql ranks the candidates to identify the best matching one for the given NL query. Extensive experiments are performed to study Metasql on two public NLIDB benchmarks. The results show that the performance of the translation models can be effectively improved using Metasql.