Query2Vec: An Evaluation of NLP Techniques for Generalized Workload Analytics

no code implementations • 17 Jan 2018 • Shrainik Jain, Bill Howe, Jiaqi Yan, Thierry Cruanes

We find that these general approaches, when trained on a large corpus of SQL queries, provides a robust foundation for a variety of workload analysis tasks and database features, without requiring application-specific feature engineering.

Feature Engineering Transfer Learning