SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising
Kuan Xu, Yongbo Wang, Yongliang Wang, Zihao Wang, Zujie Wen, Yang Dong
Abstract
On the WikiSQL benchmark, most methods tackle the challenge of text-to-SQL with predefined sketch slots and build sophisticated sub-tasks to fill these slots. Though achieving promising results, these methods suffer from over-complex model structure. In this paper, we present a simple yet effective approach that enables auto-regressive sequence-to-sequence model to robust text-to-SQL generation. Instead of formulating the task of text-to-SQL as slot-filling, we propose to train sequence-to-sequence model with Schema-aware Denoising (SeaD), which consists of two denoising objectives that train model to either recover input or predict output from two novel erosion and shuffle noises. These model-agnostic denoising objectives act as the auxiliary tasks for structural data modeling during sequence-to-sequence generation. In addition, we propose a clause-sensitive execution guided (EG) decoding strategy to overcome the limitation of EG decoding for generative model. The experiments show that the proposed method improves the performance of sequence-to-sequence model in both schema linking and grammar correctness and establishes new state-of-the-art on WikiSQL benchmark. Our work indicates that the capacity of sequence-to-sequence model for text-to-SQL may have been under-estimated and could be enhanced by specialized denoising task.
BibTeX
@inproceedings{xu-etal-2022-sead,
title = "{S}ea{D}: End-to-end Text-to-{SQL} Generation with Schema-aware Denoising",
author = "Xu, Kuan and
Wang, Yongbo and
Wang, Yongliang and
Wang, Zihao and
Wen, Zujie and
Dong, Yang",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.141/",
doi = "10.18653/v1/2022.findings-naacl.141",
pages = "1845--1853"
}