SQL-Encoder: Improving NL2SQL In-Context Learning Through a Context-Aware Encoder

arXiv:2403.16204v1 Announce Type: new
Abstract: Detecting structural similarity between queries is essential for selecting examples in in-context learning models. However, assessing structural similarity based solely on the natural language expressions of queries, without considering SQL queries, presents a significant challenge. This paper explores the significance of this similarity metric and proposes a model for accurately estimating it. To achieve this, we leverage a dataset comprising 170k question pairs, meticulously curated to train a similarity prediction model. Our comprehensive evaluation demonstrates …

abstract arxiv challenge context cs.cl cs.db cs.hc encoder examples however improving in-context learning language natural natural language paper queries significance sql sql queries through type