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

arXiv:2406.00014v1 Announce Type: cross
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 …

abstract arxiv beyond capabilities challenge cs.ai cs.cl cs.db cs.ir data database databases ehr electronic electronic health record health information language natural natural language process queries query question questions record request retrieval sql sql queries sql query type via