SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising

by   Kuan Xuan, et al.

In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture. In this paper, we present a simple yet effective approach that adapts transformer-based seq-to-seq model to robust text-to-SQL generation. Instead of inducing constraint to decoder or reformat the task as slot-filling, we propose to train seq-to-seq 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 denoising objectives acts as the auxiliary tasks for better modeling the structural data in S2S generation. In addition, we improve and 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 seq-to-seq model in both schema linking and grammar correctness and establishes new state-of-the-art on WikiSQL benchmark. The results indicate that the capacity of vanilla seq-to-seq architecture for text-to-SQL may have been under-estimated.



There are no comments yet.


page 1

page 2

page 3

page 4


X-SQL: reinforce schema representation with context

In this work, we present X-SQL, a new network architecture for the probl...

Mention Extraction and Linking for SQL Query Generation

On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically...

Improving Text-to-SQL with Schema Dependency Learning

Text-to-SQL aims to map natural language questions to SQL queries. The s...

Grammar-based Neural Text-to-SQL Generation

The sequence-to-sequence paradigm employed by neural text-to-SQL models ...

IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation

Context-dependent text-to-SQL task has drawn much attention in recent ye...

End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task

In this work, we focus on two crucial components in the cross-domain tex...

Zero-shot Text-to-SQL Learning with Auxiliary Task

Recent years have seen great success in the use of neural seq2seq models...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.