-
spider
scripts and baselines for Spider: Yale complex and cross-domain semantic parsing and text-to-SQL challenge
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Hey all - I'm currently working on a self-service, natural language BI tool that aims to go beyond the base "text to sql" of current tools. I've got the bones built, but I'm struggling to develop a suite of test questions (ideally with complex metrics like "What is our profitability" or abstract concepts like "How are our sales doing"). Does anyone know of any lists of questions (and ideally answers on the quantitative questions) for the MS adventureworks database, or any other complex (30+ table) public test databases? I've looked at Spider, but most of the datasets are too small to simulate real-world business datasets, and the questions are more "can you write fancy SQL" and less "can you answer a vague stakeholder question on unknown data".