zzp1012 / jointly-embedding

jointly embedding both texts and knowledge graph into same space

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

jointly-embedding

Abstract

jointly embedding both triplets from knowledge graph and text corpus.

Requirements

  1. Make sure GPU is avaible and CUDA>=10.2 has been installed on your computer. You can check it with
        nvidia-smi
  2. Simply create an virtural environment with python>=3.8 and run pip install -r requirements.txt to download the required packages. If you use anaconda3 or miniconda, you can run following instructions to download the required packages in python.
        conda create -y -n joint python=3.8
        conda activate joint
        pip install pip --upgrade
        pip install -r requirements.txt
        conda activate joint

Contributing

if you would like to contribute some codes, please submit a PR, and feel free to post issues via Github.

Contact

Please contact zzp1012@sjtu.edu.cn if you have any question on the codes.


UM-SJTU Joint Institute 交大密西根学院

About

jointly embedding both texts and knowledge graph into same space

License:MIT License


Languages

Language:Python 100.0%