Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation
arXiv:2402.17144 · doi:10.1109/ICDE60146.2024.00143
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.
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- Multi-Stage Document Ranking with BERT
- Mutual Information and Diverse Decoding Improve Neural Machine Translation
- DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
- A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability
- Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases
- Evaluating the Text-to-SQL Capabilities of Large Language Models
- SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)
- NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting
- Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation
- PairReranker: Pairwise Reranking for Natural Language Generation