Global Reasoning over Database Structures for Text-to-SQL Parsing

by   Ben Bogin, et al.

State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time. When tested against complex databases that are unobserved at training time (zero-shot), the parser often struggles to select the correct set of database constants in the new database, due to the local nature of decoding. In this work, we propose a semantic parser that globally reasons about the structure of the output query to make a more contextually-informed selection of database constants. We use message-passing through a graph neural network to softly select a subset of database constants for the output query, conditioned on the question. Moreover, we train a model to rank queries based on the global alignment of database constants to question words. We apply our techniques to the current state-of-the-art model for Spider, a zero-shot semantic parsing dataset with complex databases, increasing accuracy from 39.4 to 47.4


page 1

page 2

page 3

page 4


Grounded Adaptation for Zero-shot Executable Semantic Parsing

We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing...

Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing

Research on parsing language to SQL has largely ignored the structure of...

SmBoP: Semi-autoregressive Bottom-up Semantic Parsing

The de-facto standard decoding method for semantic parsing in recent yea...

Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

Building a semantic parser quickly in a new domain is a fundamental chal...

KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers

The goal of database question answering is to enable natural language qu...

Few-Shot Semantic Parsing for New Predicates

In this work, we investigate the problems of semantic parsing in a few-s...

Hierarchical Human Parsing with Typed Part-Relation Reasoning

Human parsing is for pixel-wise human semantic understanding. As human b...