Wav2SQL: Direct Generalizable Speech-To-SQL Parsing

05/21/2023
by   Huadai Liu, et al.
0

Speech-to-SQL (S2SQL) aims to convert spoken questions into SQL queries given relational databases, which has been traditionally implemented in a cascaded manner while facing the following challenges: 1) model training is faced with the major issue of data scarcity, where limited parallel data is available; and 2) the systems should be robust enough to handle diverse out-of-domain speech samples that differ from the source data. In this work, we propose the first direct speech-to-SQL parsing model Wav2SQL which avoids error compounding across cascaded systems. Specifically, 1) to accelerate speech-driven SQL parsing research in the community, we release a large-scale and multi-speaker dataset MASpider; 2) leveraging the recent progress in the large-scale pre-training, we show that it alleviates the data scarcity issue and allow for direct speech-to-SQL parsing; and 3) we include the speech re-programming and gradient reversal classifier techniques to reduce acoustic variance and learned style-agnostic representation, improving generalization to unseen out-of-domain custom data. Experimental results demonstrate that Wav2SQL avoids error compounding and achieves state-of-the-art results by up to 2.5% accuracy improvement over the baseline.

READ FULL TEXT

page 3

page 4

research
08/29/2022

A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions

Text-to-SQL parsing is an essential and challenging task. The goal of te...
research
01/04/2022

Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question

Speech-based inputs have been gaining significant momentum with the popu...
research
10/23/2022

Towards Generalizable and Robust Text-to-SQL Parsing

Text-to-SQL parsing tackles the problem of mapping natural language ques...
research
06/22/2021

KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers

The goal of database question answering is to enable natural language qu...
research
05/23/2023

Exploring Chain-of-Thought Style Prompting for Text-to-SQL

Conventional supervised approaches for text-to-SQL parsing often require...
research
04/12/2021

Learning to Synthesize Data for Semantic Parsing

Synthesizing data for semantic parsing has gained increasing attention r...
research
09/14/2022

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers

This paper aims to improve the performance of text-to-SQL parsing by exp...

Please sign up or login with your details

Forgot password? Click here to reset