KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR

TL;DR

This paper presents a novel framework for converting natural language questions into SQL queries in electronic health records, effectively handling out-of-domain questions and verifying query correctness through execution, improving adaptability and performance.

Contribution

Introduces a question templization and verification framework using fine-tuned GPT-3.5 to improve robustness in text-to-SQL conversion for EHR data.

Findings

Effective handling of out-of-domain questions.

Improved performance on EHRSQL-2024 benchmark.

Competitive results in the official leaderboard.

Abstract

Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request information beyond the database's scope or exceed the system's capabilities. In this paper, we introduce a novel text-to-SQL framework that robustly handles out-of-domain questions and verifies the generated queries with query execution.Our framework begins by standardizing the structure of questions into a templated format. We use a powerful large language model (LLM), fine-tuned GPT-3.5 with detailed prompts involving the table schemas of the EHR database system. Our experimental results demonstrate the effectiveness of our framework on the EHRSQL-2024 benchmark benchmark, a shared task in the ClinicalNLP workshop. Although a straightforward fine-tuning of GPT shows promising results on the development set, it struggled with the out-of-domain questions in the test set. With our framework, we improve our system's adaptability and achieve competitive performances in the official leaderboard of the EHRSQL-2024 challenge.