https://github.com/osu-nlp-group/auto-sql-correction
Code, data, and model of paper "Text-to-SQL Error Correction with Language Models of Code" (ACL'23)
https://github.com/osu-nlp-group/auto-sql-correction
code-editor code-generation natural-language-interface text-to-sql
Last synced: 11 months ago
JSON representation
Code, data, and model of paper "Text-to-SQL Error Correction with Language Models of Code" (ACL'23)
- Host: GitHub
- URL: https://github.com/osu-nlp-group/auto-sql-correction
- Owner: OSU-NLP-Group
- Created: 2023-05-03T23:00:49.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2024-08-22T14:28:38.000Z (almost 2 years ago)
- Last Synced: 2025-06-05T04:42:33.195Z (about 1 year ago)
- Topics: code-editor, code-generation, natural-language-interface, text-to-sql
- Language: Python
- Homepage: https://arxiv.org/abs/2305.13073
- Size: 49.8 KB
- Stars: 30
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Auto-SQL-Correction
Code, data, and model for our ACL 2023 paper [Text-to-SQL Error Correction with Language Models of Code](https://arxiv.org/abs/2305.13073).
## Table of Contents
1. Installation
2. Data
3. Preprocessing
4. Training
5. Evaluation
6. Citation
## Installation
Please run the following commands to create a conda environment in Python 3.9 with the required packages.
```sh
conda create -n sqledit python=3.9 pip
conda activate sqledit
pip install -r requirements.txt
```
## Data
Please first download the original Spider dataset from this [link](https://drive.google.com/uc?export=download&id=1TqleXec_OykOYFREKKtschzY29dUcVAQ) and unzip it in the `data/` folder.
```sh
unzip spider.zip -d data/
```
Then, please download our synthesized SQL error correction data from this [link](https://buckeyemailosu-my.sharepoint.com/:f:/g/personal/chen_8336_buckeyemail_osu_edu/EjAxbCHp5q9BgT9Ljyq60xUBN_gEFGeOLQFSl5NusgV9VQ?e=EpB555) and also put them in the `data/` folder.
The `data/` folder should be organized as follows:
```
.
├─── data
│ ├─── spider
│ ├─── ...
│ ├─── spider-dev-bridge.json
│ ├─── spider-dev-codet5.json
│ ├─── spider-dev-smbop.json
│ ├─── spider-train-bridge.json
│ ├─── spider-train-codet5.json
│ ├─── spider-train-smbop.json
│ ├─── sqledit_dev_gold.sql
│ ...
```
## Preprocessing
```sh
python run.py --preproc --use_content --query_type pydict --edit_type program --base_parser smbop
```
## Training
```sh
mkdir model
python run.py --train --load_checkpoint Salesforce/codet5-base --save_checkpoint model/codet5-sqledit --seed 42 --gpu 0
```
## Evaluation
```sh
python run.py --eval --load_checkpoint model/codet5-sqledit --gpu 0
```
### Model Checkpoints
You may download our pre-trained model checkpoints from this [link](https://buckeyemailosu-my.sharepoint.com/:f:/g/personal/chen_8336_buckeyemail_osu_edu/Er_mV3sNNotPoaCivzCLwDQBBuI5rRR1fymCJpshIrJEZA?e=U4Xz2t). It includes our `CodeT5-PyDict+Program` model trained for the three text-to-SQL base parser in our paper.
## Citation
```
@inproceedings{chen-etal-2023-sqledit,
title = "Text-to-SQL Error Correction with Language Models of Code",
author = "Chen, Ziru and
Chen, Shijie and
White, Michael and
Mooney, Raymond and
Payani, Ali and
Srinivasa, Jayanth and
Su, Yu and
Sun, Huan",
booktitle = "Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/2305.13073"
}
```