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

arXiv: https://arxiv.org/abs/1909.06182 · HTML: https://mlsanity.com/paper/1909.06182/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 5 of 5)

- [Factoring Statutory Reasoning as Language Understanding Challenges](https://mlsanity.com/paper/2105.07903/) (2021)
- [CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codex](https://mlsanity.com/paper/2204.08941/) (2022)
- [Translating synthetic natural language to database queries: a polyglot deep learning framework](https://mlsanity.com/paper/2104.07010/) (2021)
- [Demonstrating CAT: Synthesizing Data-Aware Conversational Agents for Transactional Databases](https://mlsanity.com/paper/2203.14144/) (2022)
- [Conversational Data Exploration: A Game-Changer for Designing Data Science Pipelines](https://mlsanity.com/paper/2311.06695/) (2023)

## Abstract (arXiv)

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.