Recent advances in deep learning have led to a new generation of natural language interfaces. However, understanding natural language questions and translating them accurately to SQL is a challenging task, and thus Natural Language Interfaces for Databases (NLIDBs) have not yet made their way into practical tools and commercial products.
Therefore, in one of our projects we are working on a novel data exploration tool with a robust natural language interface called DBPal. DBPal leverages recent advances in deep neural network models to make query understanding more robust. More projects in this research area are described below.
DBPal is an end-to-end approach to translating natural language utterances into SQL statements using a neural machine translation model. The system includes a data generation pipeline to create SQL/natural language pairs, a translation backend based on a sequence-to-sequence model and a userfriendly front end.
CAT: Conversational Agents for Database Transactions
CAT synthesizes conversational agents for a given OLTP application with only minimal manual overhead. The main idea is that for a given relational database and a set of transactions, CAT synthesizes the required training data with weak supervision to train a state-of-the-art conversational model that allows user to interact with the database.