Deep Learning on Graphs for Natural Language Processing Demo

The repository contains code examples for DLG4NLP tutorials at NAACL 2021, SIGIR 2021, KDD 2021, IJCAI 2021, AAAI 2022 and TheWebConf 2022.

Slides can be downloaded from here.

Get Started

You will need to install our graph4nlp library in order to run the demo code. Please follow the following environment setup instructions. Please also refer to the graph4nlp repository page for more details on how to use the library.

Environment setup

1. Create virtual environment

conda create --name graph4nlp python=3.8
conda activate graph4nlp

2. Install graph4nlp library

• Clone the github repo

git clone -b [branch_version] https://github.com/graph4ai/graph4nlp.git
cd graph4nlp

Please choose the branch version corresponding to the demo version as shown in the table below.

• Then run ./configure (or ./configure.bat if you are using Windows 10) to config your installation. The configuration program will ask you to specify your CUDA version. If you do not have a GPU, please choose 'cpu'.

./configure

• Finally, install the package

python setup.py install

3. Install other packages

pip install torchtext
pip install notebook

4. Set up StanfordCoreNLP (for static graph construction only, unnecessary for this demo because preprocessed data is provided)

• Download StanfordCoreNLP
• Go to the root folder and start the server

java -mx4g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer -port 9000 -timeout 15000

Start Jupyter notebook and run the demo

After complete the above steps, you can start the jupyter notebook server to run the demo:

cd graph4nlp_demo/XYZ
jupyter notebook

Note that you will need to change XYZ to the specific folder name.

Additional Resources:

• Graph4NLP library
• DLG4NLP website
• DLG4NLP survey
• DLG4NLP literature repo