MIGA: A Unified Multi-Task Generation Framework for Conversational Text-to-SQL
Yingwen Fu, Wenjie Ou, Zhou Yu, Yue Lin
Abstract
Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most advanced conversational text-to-SQL methods are incompatible with generative pre-trained language models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs’ ability to tackle conversational text-to-SQL. In the pre-training stage, MIGA first decomposes the main task into several related sub-tasks and then unifies them into the same sequence-to-sequence (Seq2Seq) paradigm with task-specific natural language prompts to boost the main task from multi-task training. Later in the fine-tuning stage, we propose four SQL perturbations to alleviate the error propagation problem. MIGA tends to achieve state-of-the-art performance on two benchmarks (SparC and CoSQL). We also provide extensive analyses and discussions to shed light on some new perspectives for conversational text-to-SQL.
BibTeX
@article{Fu_Ou_Yu_Lin_2023, title={MIGA: A Unified Multi-Task Generation Framework for Conversational Text-to-SQL}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26504}, DOI={10.1609/aaai.v37i11.26504}, abstractNote={Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most advanced conversational text-to-SQL methods are incompatible with generative pre-trained language models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs’ ability to tackle conversational text-to-SQL. In the pre-training stage, MIGA first decomposes the main task into several related sub-tasks and then unifies them into the same sequence-to-sequence (Seq2Seq) paradigm with task-specific natural language prompts to boost the main task from multi-task training. Later in the fine-tuning stage, we propose four SQL perturbations to alleviate the error propagation problem. MIGA tends to achieve state-of-the-art performance on two benchmarks (SparC and CoSQL). We also provide extensive analyses and discussions to shed light on some new perspectives for conversational text-to-SQL.}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Fu, Yingwen and Ou, Wenjie and Yu, Zhou and Lin, Yue}, year={2023}, month={Jun.}, pages={12790-12798} }