An Investigation Between Schema Linking and Text-to-SQL Performance
This research addresses the problem of interpreting neural Text-to-SQL models for researchers and developers by providing a method for analyzing internal model behavior.
This paper investigates the relationship between schema linking and Text-to-SQL performance to improve the interpretability of neural models. By providing ground-truth schema linking annotations for the Spider dataset, the study enables detailed analysis of state-of-the-art neural models.
Text-to-SQL is a crucial task toward developing methods for understanding natural language by computers. Recent neural approaches deliver excellent performance; however, models that are difficult to interpret inhibit future developments. Hence, this study aims to provide a better approach toward the interpretation of neural models. We hypothesize that the internal behavior of models at hand becomes much easier to analyze if we identify the detailed performance of schema linking simultaneously as the additional information of the text-to-SQL performance. We provide the ground-truth annotation of schema linking information onto the Spider dataset. We demonstrate the usefulness of the annotated data and how to analyze the current state-of-the-art neural models.