Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker
This addresses the challenge of accurately converting natural language to SQL for database access, though it is incremental as it builds on existing generative models.
The paper tackles the problem of improving text-to-SQL translation by proposing a discriminative re-ranker that selects the best SQL query from a generator's beam output, achieving a top 4 score on the Spider leaderboard.
To access data stored in relational databases, users need to understand the database schema and write a query using a query language such as SQL. To simplify this task, text-to-SQL models attempt to translate a user's natural language question to corresponding SQL query. Recently, several generative text-to-SQL models have been developed. We propose a novel discriminative re-ranker to improve the performance of generative text-to-SQL models by extracting the best SQL query from the beam output predicted by the text-to-SQL generator, resulting in improved performance in the cases where the best query was in the candidate list, but not at the top of the list. We build the re-ranker as a schema agnostic BERT fine-tuned classifier. We analyze relative strengths of the text-to-SQL and re-ranker models across different query hardness levels, and suggest how to combine the two models for optimal performance. We demonstrate the effectiveness of the re-ranker by applying it to two state-of-the-art text-to-SQL models, and achieve top 4 score on the Spider leaderboard at the time of writing this article.