This is the project containing source code for the paper LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations in ACL 2021 main conference. If you find it useful, please cite our work.

    @inproceedings{cao-etal-2021-lgesql,
            title = "{LGESQL}: Line Graph Enhanced Text-to-{SQL} Model with Mixed Local and Non-Local Relations",
            author = "Cao, Ruisheng  and
            Chen, Lu  and
            Chen, Zhi  and
            Zhao, Yanbin  and
            Zhu, Su  and
            Yu, Kai",
            booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
            month = aug,
            year = "2021",
            address = "Online",
            publisher = "Association for Computational Linguistics",
            url = "https://aclanthology.org/2021.acl-long.198",
            doi = "10.18653/v1/2021.acl-long.198",
            pages = "2541--2555",
    }

The following commands are provided in setup.sh.

1. Firstly, create conda environment text2sql:

• In our experiments, we use torch==1.6.0 and dgl==0.5.3 with CUDA version 10.1

  conda create -n text2sql python=3.6
  source activate text2sql
  pip install torch==1.6.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html
  pip install -r requirements.txt
  

2. Next, download dependencies:

    python -c "import stanza; stanza.download('en')"
    python -c "from embeddings import GloveEmbedding; emb = GloveEmbedding('common_crawl_48', d_emb=300)"
    python -c "import nltk; nltk.download('stopwords')"
   

3. Download pre-trained language models from Hugging Face Model Hub, such as bert-large-whole-word-masking and electra-large-discriminator, into the pretrained_models directory. The vocab file for glove.42B.300d is also pulled: (please ensure that Git LFS is installed)

    mkdir -p pretrained_models && cd pretrained_models
    git lfs install
    git clone https://huggingface.co/bert-large-uncased-whole-word-masking
    git clone https://huggingface.co/google/electra-large-discriminator
    mkdir -p glove.42b.300d && cd glove.42b.300d
    wget -c http://nlp.stanford.edu/data/glove.42B.300d.zip && unzip glove.42B.300d.zip
    awk -v FS=' ' '{print $1}' glove.42B.300d.txt > vocab_glove.txt
   

1. Download, unzip and rename the spider.zip into the directory data.

2. Merge the data/train_spider.json and data/train_others.json into one single dataset data/train.json.

3. Preprocess the train and dev dataset, including input normalization, schema linking, graph construction and output actions generation. (Our preprocessed dataset can be downloaded here)

    ./run/run_preprocessing.sh
   

Training LGESQL models with GLOVE, BERT and ELECTRA respectively:

• msde: mixed static and dynamic embeddings

• mmc: multi-head multi-view concatenation

  ./run/run_lgesql_glove.sh [mmc|msde]
  ./run/run_lgesql_plm.sh [mmc|msde] bert-large-uncased-whole-word-masking
  ./run/run_lgesql_plm.sh [mmc|msde] electra-large-discriminator
  

1. Create the directory saved_models, save the trained model and its configuration (at least containing model.bin and params.json) into a new directory under saved_models, e.g. saved_models/electra-msde-75.1/.

2. For evaluation, see run/run_evaluation.sh and run/run_submission.sh (eval from scratch) for reference.

3. Model instances and submission scripts are available in codalab:plm and google drive: including submitted BERT and ELECTRA models. Codes and model for GLOVE are deprecated.

Dev and test EXACT MATCH ACC in the official leaderboard, also provided in the results directory:

We would like to thank Tao Yu, Yusen Zhang and Bo Pang for running evaluations on our submitted models. We are also grateful to the flexible semantic parser TranX that inspires our works.