GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
This work addresses the challenge of generating SQL queries from natural language for database interactions, representing an incremental improvement with specific gains in accuracy and robustness.
The paper tackles the problem of Text-to-SQL parsing by proposing Grammar Pre-training (GP) to decode deep relations between questions and databases, achieving a performance of 72.8 on the dev set and 69.8 on the test set of the Spider dataset.
A new method for Text-to-SQL parsing, Grammar Pre-training (GP), is proposed to decode deep relations between question and database. Firstly, to better utilize the information of databases, a random value is added behind a question word which is recognized as a column, and the new sentence serves as the model input. Secondly, initialization of vectors for decoder part is optimized, with reference to the former encoding so that question information can be concerned. Finally, a new approach called flooding level is adopted to get the non-zero training loss which can generalize better results. By encoding the sentence with GRAPPA and RAT-SQL model, we achieve better performance on spider, a cross-DB Text-to-SQL dataset (72.8 dev, 69.8 test). Experiments show that our method is easier to converge during training and has excellent robustness.