Text-To-SQL
138 papers with code • 6 benchmarks • 14 datasets
Text-to-SQL is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.
( Image credit: SyntaxSQLNet )
Libraries
Use these libraries to find Text-To-SQL models and implementationsDatasets
Latest papers
ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought
Recently Large Language Models (LLMs) have been proven to have strong abilities in various domains and tasks.
TUR2SQL: A Cross-Domain Turkish Dataset For Text-to-SQL
The field of converting natural language into corresponding SQL queries using deep learning techniques has attracted significant attention in recent years.
Benchmarking and Improving Text-to-SQL Generation under Ambiguity
Research in Text-to-SQL conversion has been largely benchmarked against datasets where each text query corresponds to one correct SQL.
Semantic Decomposition of Question and SQL for Text-to-SQL Parsing
However, this strategy encounters two major obstacles: (1) existing datasets lack question decomposition; (2) due to the syntactic complexity of SQL, most complex queries cannot be disentangled into sub-queries that can be readily recomposed.
MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations
Additionally, our analysis uncovers the semantic predispositions in LLMs and reveals the impact of recency bias for information presented in long contexts.
Selective Demonstrations for Cross-domain Text-to-SQL
Large language models (LLMs) with in-context learning have demonstrated impressive generalization capabilities in the cross-domain text-to-SQL task, without the use of in-domain annotations.
Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
We aim to understand why the incorporation of structural information inherent in graph data can improve the prediction performance of LLMs.
Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval
Open-domain table question answering aims to provide answers to a question by retrieving and extracting information from a large collection of tables.
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
Our explorations highlight open-source LLMs' potential in Text-to-SQL, as well as the advantages and disadvantages of the supervised fine-tuning.
C3: Zero-shot Text-to-SQL with ChatGPT
This paper proposes a ChatGPT-based zero-shot Text-to-SQL method, dubbed C3, which achieves 82. 3\% in terms of execution accuracy on the holdout test set of Spider and becomes the state-of-the-art zero-shot Text-to-SQL method on the Spider Challenge.