RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers

11/10/2019
by   Bailin Wang, et al.
0

When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas. The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query. We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder. On the challenging Spider dataset this framework boosts the exact match accuracy to 53.7 47.4 addition, we observe qualitative improvements in the model's understanding of schema linking and alignment.

READ FULL TEXT
research
06/27/2019

Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parsers

When translating natural language questions into SQL queries to answer q...
research
11/01/2021

SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL

The Text-to-SQL task, aiming to translate the natural language of the qu...
research
09/30/2020

A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing

In Text-to-SQL semantic parsing, selecting the correct entities (tables ...
research
08/02/2021

Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL

Natural language to SQL (NL2SQL) aims to parse a natural language with a...
research
05/14/2022

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

Relational structures such as schema linking and schema encoding have be...
research
04/10/2021

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

Given a database schema, Text-to-SQL aims to translate a natural languag...
research
09/28/2022

Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding

Most recent research on Text-to-SQL semantic parsing relies on either pa...

Please sign up or login with your details

Forgot password? Click here to reset