In this paper, we propose a novel SQL guided pre-training framework STAR for
context-dependent text-to-SQL parsing, which leverages contextual information
to enrich natural language (NL) utterance and table schema representations for
text-to-SQL conversations. Concretely, we propose two novel pre-training
objectives which respectively explore the context-dependent interactions of NL
utterances and SQL queries within each text-to-SQL conversation: (i) schema
state tracking (SST) objective that tracks and explores the schema states of
context-dependent SQL queries in the form of schema-states by predicting and
updating the value of each schema slot during interaction; (ii) utterance
dependency tracking (UDT) objective that employs weighted contrastive learning
to pull together two semantically similar NL utterances and push away the
representations of semantically dissimilar NL utterances within each
conversation. In addition, we construct a high-quality large-scale
context-dependent text-to-SQL conversation corpus to pre-train STAR. Extensive
experiments show that STAR achieves new state-of-the-art performance on two
downstream benchmarks (SParC and CoSQL), significantly outperforming previous
pre-training methods and ranking first on the leaderboard. We believe the
release of the constructed corpus, codebase and pre-trained STAR checkpoints
would push forward the research in this area. For reproducibility, we release
our code and data at
this https URL.

本文提出了一种新的基于 SQL 引导的预训练框架 STAR，用于上下文相关的文本到 SQL 解析，通过利用上下文信息，丰富自然语言（NL）话语和表模式表示，以解决文本到 SQL 解析中的问题，并取得了两个下游基准测试（SParC 和 CoSQL）的新最高性能，该研究可推动该领域的研究。