ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handling
This work addresses the challenge of discerning unanswerable queries in text-to-SQL tasks for medical domain applications, representing an incremental improvement.
The paper tackles the problem of generating accurate SQL queries from medical record inquiries, particularly for unanswerable queries, by introducing probabilistic threshold filtering and error handling methods, achieving practical applicability even without model parameter access.
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 schema errors are mitigated by executing queries on the actual database. We experimentally verified that our method can filter unanswerable questions, which can be widely utilized even when the parameters of the model are not accessible, and that it can be effectively utilized in practice.