GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Last update: Jan 09, 2023

Overview

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Code and model from our AAAI 2021 paper

Updates

[2020/02/05] Support to run the model on own databases and queries. Check out the notebook.

Abstract

Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present a model pre-training framework, Generation-Augmented Pre-training (GAP), that jointly learns representations of natural language utterances and table schemas by leveraging generation models to generate pre-train data. GAP MODEL is trained on 2M utterance-schema pairs and 30K utterance-schema-SQL triples, whose utterances are produced by generative models. Based on experimental results, neural semantic parsers that leverage GAP MODEL as a representation encoder obtain new state-of-the-art results on both SPIDER and CRITERIA-TO-SQL benchmarks.

Setup

conda create --name gap-text2sql python=3.7
source activate gap-text2sql
conda install pytorch=1.5 cudatoolkit=10.2 -c pytorch
pip install -r requirements.txt
python -c "import nltk; nltk.download('stopwords'); nltk.download('punkt')"

Download the dataset

pip install gdown
cd rat-sql-gap
gdown --id 1_AckYkinAnhqmRQtGsQgUKAnTHxxX5J0
unzip spider.zip
bash data/spider/generate.sh ./spider

Build dataset directory

mkdir data/spider-bart
cp ./spider/tables.json data/spider-bart/
cp ./spider/train_spider.json data/spider-bart/
cp ./spider/train_others.json data/spider-bart/
cp ./spider/dev.json data/spider-bart/
ln -s $(pwd)/spider/database data/spider-bart/database

Download the library

mkdir third_party
wget http://nlp.stanford.edu/software/stanford-corenlp-full-2018-10-05.zip
unzip stanford-corenlp-full-2018-10-05.zip -d third_party/

Start the Stanford library

pushd third_party/stanford-corenlp-full-2018-10-05
nohup java -mx4g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer -port 8999 -timeout 15000 > server.log &
popd

Download the checkpoint

mkdir -p logdir/bart_run_1/bs\=12\,lr\=1.0e-04\,bert_lr\=1.0e-05\,end_lr\=0e0\,att\=1/
mkdir ie_dirs
aws s3 cp s3://gap-text2sql-public/checkpoint-artifacts/gap-finetuned-checkpoint logdir/bart_run_1/bs\=12\,lr\=1.0e-04\,bert_lr\=1.0e-05\,end_lr\=0e0\,att\=1/model_checkpoint-00041000

mkdir -p pretrained_checkpoint
aws s3 cp s3://gap-text2sql-public/checkpoint-artifacts/pretrained-checkpoint pretrained_checkpoint/pytorch_model.bin

Alternatively, you can download them here if you don't have awscli: gap-finetuned-checkpoint and pretrained-checkpoint

curl https://gap-text2sql-public.s3.amazonaws.com/checkpoint-artifacts/gap-finetuned-checkpoint -o logdir/bart_run_1/bs\=12\,lr\=1.0e-04\,bert_lr\=1.0e-05\,end_lr\=0e0\,att\=1/model_checkpoint-00041000
curl https://gap-text2sql-public.s3.amazonaws.com/checkpoint-artifacts/pretrained-checkpoint -o pretrained_checkpoint/pytorch_model.bin

Preprocess dataset

python run.py preprocess experiments/spider-configs/gap-run.jsonnet

Inference

python run.py eval experiments/spider-configs/gap-run.jsonnet

You then get the inference results and evaluation results in the paths:ie_dirs/bart_run_1_true_1-step41000.infer and ie_dirs/bart_run_1_true_1-step41000.eval.

Training

python run.py train experiments/spider-configs/gap-run.jsonnet

Security

See CONTRIBUTING for more information.

License

This project is licensed under the Apache-2.0 License.

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Related tags

Overview

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Updates

Abstract

Setup

Download the dataset

Build dataset directory

Download the library

Start the Stanford library

Download the checkpoint

Preprocess dataset

Inference

Training

Security

License

Owner

Amazon Web Services - Labs

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

2021搜狐校园文本匹配算法大赛baseline

Lattice methods in TensorFlow

✔👉A Centralized WebApp to Ensure Road Safety by checking on with the activities of the driver and activating label generator using NLP.

基于GRU网络的句子判断程序/A program based on GRU network for judging sentences

Research code for the paper "Fine-tuning wav2vec2 for speaker recognition"

ConferencingSpeech2022; Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge

This project consists of data analysis and data visualization (done using python)of all IPL seasons from 2008 to 2019 and answering the most asked questions about the IPL.

Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT.

Speech to text streamlit app

spaCy plugin for Transformers , Udify, ELmo, etc.

Sequence-to-Sequence learning using PyTorch

PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers

Interactive Jupyter Notebook Environment for using the GPT-3 Instruct API

skweak: A software toolkit for weak supervision applied to NLP tasks

Code for our ACL 2021 (Findings) Paper - Fingerprinting Fine-tuned Language Models in the wild .

A high-level yet extensible library for fast language model tuning via automatic prompt search

ByT5: Towards a token-free future with pre-trained byte-to-byte models

MEDIALpy: MEDIcal Abbreviations Lookup in Python

:mag: Transformers at scale for question answering & neural search. Using NLP via a modular Retriever-Reader-Pipeline. Supporting DPR, Elasticsearch, HuggingFace's Modelhub...