arXiv (Cornell University) · 2023 · 25 citations · 0 references
ChatbotEngineeringCorpus LinguisticsText MiningNatural Language ProcessingZero-shot LearningInformation RetrievalData ScienceComputational LinguisticsMachine TranslationDialogue ManagementNatural Language InterfaceSpider ChallengeNlp TaskComputer ScienceClear PromptingRetrieval Augmented GenerationHoldout Test SetZero-shot Text-to-sqlText Processing
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.