SQL Parsing

9 papers with code • 8 benchmarks • 2 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing

alibabaresearch/damo-convai 28 Jun 2022

The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i. e., properly recognizing mentions of unseen columns or tables when generating SQLs.

Improving Text-to-SQL Evaluation Methodology

jkkummerfeld/text2sql-data ACL 2018

Second, we show that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries; therefore, we propose a complementary dataset split for evaluation of future work.

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

benbogin/spider-schema-gnn ACL 2019

Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time.

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

benbogin/spider-schema-gnn-global IJCNLP 2019

State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time.

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

sanxing-chen/linking-tale COLING 2020

In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and the SQL query to the structured knowledge in the database.

Optimizing Deeper Transformers on Small Datasets

BorealisAI/DT-Fixup ACL 2021

This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.

Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing

PaddlePaddle/Research EMNLP 2021

For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries.

Learning to Synthesize Data for Semantic Parsing

berlino/tensor2struct-public NAACL 2021

Moreover, explicitly modeling compositions using PCFG leads to a better exploration of unseen programs, thus generate more diverse data.

Weakly Supervised Text-to-SQL Parsing through Question Decomposition

tomerwolgithub/question-decomposition-to-sql Findings (NAACL) 2022

Given questions, their QDMR structures (annotated by non-experts or automatically predicted), and the answers, we are able to automatically synthesize SQL queries that are used to train text-to-SQL models.