Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing
This work addresses a key challenge in making Text-to-SQL systems more robust for real-world applications, though it is incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of compositional generalization in context-dependent Text-to-SQL parsing, where models struggle with novel combinations of modification patterns, and proposes a method that improves performance by better aligning previous SQL statements with input utterances.
In the context-dependent Text-to-SQL task, the generated SQL statements are refined iteratively based on the user input utterance from each interaction. The input text from each interaction can be viewed as component modifications to the previous SQL statements, which could be further extracted as the modification patterns. Since these modification patterns could also be combined with other SQL statements, the models are supposed to have the compositional generalization to these novel combinations. This work is the first exploration of compositional generalization in context-dependent Text-to-SQL scenarios. To facilitate related studies, we constructed two challenging benchmarks named \textsc{CoSQL-CG} and \textsc{SParC-CG} by recombining the modification patterns and existing SQL statements. The following experiments show that all current models struggle on our proposed benchmarks. Furthermore, we found that better aligning the previous SQL statements with the input utterance could give models better compositional generalization ability. Based on these observations, we propose a method named \texttt{p-align} to improve the compositional generalization of Text-to-SQL models. Further experiments validate the effectiveness of our method. Source code and data are available.