Skip to content
/ idne Public

Python package for the paper "Inductive Document Network Embedding with Topic-Word Attention" (https://arxiv.org/pdf/2001.03369.pdf)

Notifications You must be signed in to change notification settings

brochier/idne

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

To run the experiments presented in the paper:

You need python 3.7 installed on your computer with pip. Optionally create a new environment (with conda):

conda create --name idne python=3.7 pip

Then run (for linux users):

git clone https://github.com/brochier/idne
cd idne
pip install -r requirements.txt 
python scripts/evaluations.py -h

Soon the code will be packaged with a Jupyter Notebook example code...

Citing

If you use this code, please consider citing the paper:

@inproceedings{brochier2020inductive,
	title={Inductive Document Network Embedding with Topic-Word Attention},
	author={Brochier, Robin and Guille, Adrien and Velcin, Julien},
	booktitle={Proceedings of the 42nd European Conference on Information Retrieval Research},
	year={2020},
	organization={Springer}
}