arXiv (Cornell University) · 2023 · 28 citations · 0 references
ComputingComputer ScienceInformation TechnologyComputational LinguisticsInformation RetrievalNatural Language ProcessingHint GenerationInformation ExtractionQuery ProcessingQuestion AnsweringStructured Query LanguageText GenerationAccuracyDatabase Query InterfacesHoldout EvaluationModel BiasPromptingQuestion Prompting
This paper proposes a ChatGPT-based zero-shot Text-to-SQL method, dubbed C3, which achieves 82.3\% in terms of execution accuracy on the holdout test set of Spider and becomes the state-of-the-art zero-shot Text-to-SQL method on the Spider Challenge. C3 consists of three key components: Clear Prompting (CP), Calibration with Hints (CH), and Consistent Output (CO), which are corresponding to the model input, model bias and model output respectively. It provides a systematic treatment for zero-shot Text-to-SQL. Extensive experiments have been conducted to verify the effectiveness and efficiency of our proposed method.