Content Enhanced BERT-based Text-to-SQL Generation

Tong Guo, Huilin Gao
10/16/2019
cs.CL

Official code: guotong1988/NL2SQL-RULE (195 stars, PyTorch, last commit 2024-10-17).

Abstract

We present a simple methods to leverage the table content for the BERT-based model to solve the text-to-SQL problem. Based on the observation that some of the table content match some words in question string and some of the table header also match some words in question string, we encode two addition feature vector for the deep model. Our methods also benefit the model inference in testing time as the tables are almost the same in training and testing time. We test our model on the WikiSQL dataset and outperform the BERT-based baseline by 3.7% in logic form and 3.7% in execution accuracy and achieve state-of-the-art.

View on arXivView PDF

Code Implementations(1)

guotong1988/NL2SQL-RULEOfficial100%
PyTorch

Content Enhanced BERT-based Text-to-SQL Generation https://arxiv.org/abs/1910.07179

19551Python, Jupyter NotebookOct 18, 20192 years ago
bertdeep-learningknowledgeknowledge-representationnl2sql+5 more

Similar Papers

HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation

84% match2023

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

82% match1 repo4182023

Using Database Rule for Weak Supervised Text-to-SQL Generation

82% match1 repo122019

Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation

81% match1 repo62025

Adapting Knowledge for Few-shot Table-to-Text Generation

81% match1 repo42023

Structure-Guided Large Language Models for Text-to-SQL Generation

81% match2024

Cite this paper

@article{guo2019content,
  title  = {Content Enhanced BERT-based Text-to-SQL Generation},
  author = {Tong Guo and Huilin Gao},
  year   = {2019},
  eprint = {1910.07179},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1910.07179}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1910.07179.svg)](https://codeofpaper.com/paper/1910.07179)

Discussion