SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.00557 · 2020

Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.00557")
get_code_for_paper("2002.00557")
have("2002.00557")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2002.00557.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2002.00557.svg)](https://syntology.ai/paper/2002.00557)

Connect an agent — have() is free.