News

GitHub1mon
Natural language to SQL on multi-table databases using LLMs with schema + sample data awareness.
Text2SQL-MultiTable is a lightweight framework for converting natural language questions into accurate SQL queries over multi-table relational databases.It leverages large language models (LLMs) like ...
GitHub9mon
GitHub - AnkurVasani2/Text_To_SQL: A powerful tool that allows users to upload SQL schema files and ask questions to automatically generate SQL queries and solve related ...
The Text to SQL Generator is a web-based application that leverages the power of Google's Generative AI (gemini-1.5-flash) to help users interact with SQL schemas and generate relevant SQL queries. By ...
IEEE1y
PS-SQL: Phrase-based Schema-Linking with Pre-trained Language Models for Text-to-SQL Parsing - IEEE Xplore
In the Text-to-SQL task, a significant challenge is enabling parsers to generalize effectively across diverse domains. Key to solving is schema-linking, which involves mapping words to the pertinent ...
Microsoft5y
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
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 ...
Microsoft3y
Bridging the Generalization Gap in Text-to-SQL Parsing with Schema Expansion
Text-to-SQL parsers map natural language questions to programs that are executable over tables to generate answers, and are typically evaluated on large-scale datasets like SPIDER (Yu et al., 2018).
marktechpost8mon
Google Cloud and Stanford Researchers Propose CHASE-SQL: An AI Framework for Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
In particular, CHASE-SQL has obtained top-tier execution accuracy ratings of 73.0% on the BIRD Text-to-SQL dataset test set and 73.01% on the development set. These outcomes have established CHASE-SQL ...