DBPal: Weak Supervision for Learning a Natural Language Interface to Databases

by   Nathaniel Weir, et al.

This paper describes DBPal, a new system to translate natural language utterances into SQL statements using a neural machine translation model. While other recent approaches use neural machine translation to implement a Natural Language Interface to Databases (NLIDB), existing techniques rely on supervised learning with manually curated training data, which results in substantial overhead for supporting each new database schema. In order to avoid this issue, DBPal implements a novel training pipeline based on weak supervision that synthesizes all training data from a given database schema. In our evaluation, we show that DBPal can outperform existing rule-based NLIDBs while achieving comparable performance to other NLIDBs that leverage deep neural network models without relying on manually curated training data for every new database schema.



There are no comments yet.


page 1

page 2

page 3

page 4


A Transfer-Learnable Natural Language Interface for Databases

Relational database management systems (RDBMSs) are powerful because the...

An End-to-end Neural Natural Language Interface for Databases

The ability to extract insights from new data sets is critical for decis...

An Encoder-Decoder Framework Translating Natural Language to Database Queries

Machine translation is going through a radical revolution, driven by the...

Dataset for a Neural Natural Language Interface for Databases (NNLIDB)

Progress in natural language interfaces to databases (NLIDB) has been sl...

DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks

Translating Natural Language Queries (NLQs) to Structured Query Language...

AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data

We propose AutoQA, a methodology and toolkit to generate semantic parser...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.