Skip to content

ColdMist/LEMON

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings

MIT License Python 3.6

Installation

Execute the following command to install the required libraries:

pip install -r requirements.txt

Data

The data used in this paper can be downloaded from Google Drive.

Steps for running the repository

Clone the github repository

git clone the <repository>

Using appropriate data directory run lm2vec.py

cd utils
python lm2vec.py

Example command for running scrips

python -u ../codes/run.py --do_train --cuda --do_test --data_path ../data/wn18rr/ --model RotatE --hidden_dim 500 --negative_sample_size 50 --batch_size 512 --gamma 6.0 --adversarial_temperature 0.5 -lr 5e-05 --max_steps 80000 -khop 3 --log_steps 5000 -nclusters 15 --dataset wn18rr -de -save models/RotatE/wn18rr/500/5e-05/512/6.0/50/0.5/80000/15/3/adv -c_low_scores --low_score_collection_threshold 200 -adv

About

No description, website, or topics provided.

Resources

License

MIT, MIT licenses found

Licenses found

MIT
LICENSE_2019
MIT
LICENSE_2020

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages