ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handling

arXiv:2404.16659v1 Announce Type: new
Abstract: Recently, deep learning-based language models have significantly enhanced text-to-SQL tasks, with promising applications in retrieving patient records within the medical domain. One notable challenge in such applications is discerning unanswerable queries. Through fine-tuning model, we demonstrate the feasibility of converting medical record inquiries into SQL queries. Additionally, we introduce an entropy-based method to identify and filter out unanswerable results. We further enhance result quality by filtering low-confidence SQL through log probability-based distribution, while grammatical and …

abstract accuracy applications arxiv challenge cs.ai cs.cl deep learning domain error filtering fine-tuning language language models medical patient queries query records sql sql query tasks text text-to-sql threshold through type