Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers
Abhijeet Awasthi, Ashutosh Sathe, Sunita Sarawagi · 2022
Text-to-SQL parsers typically struggle with databases unseen during the train time.Adapting parsers to new databases is a challenging problem due to the lack of natural language queries in the new schemas.We present REFILL, a framework for synthesizing highquality and textually diverse parallel datasets for adapting a Text-to-SQL parser to a target schema.REFILL learns to retrieve-andedit text queries from the existing schemas and transfers them to the target schema.We show that retrieving diverse existing text, masking their schema-specific tokens, and refilling with tokens relevant to the target schema, leads to significantly more diverse text queries than achievable by standard SQL-to-Text generation methods.Through experiments spanning multiple databases, we demonstrate that fine-tuning parsers on datasets synthesized using REFILL consistently outperforms the prior data-augmentation methods.