Skip to content

LivNLP/Relational-Walk-for-Knowledge-Graphs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Relational-Walk-for-Knowledge-Graphs

This repository is for the Relational Walk model (RelWalk) that performs a random walk over a KG to explain what latent structure is being captured by knowledge graph embeddings (KGEs) of entities and relations. The RelWalk model is an extension of the random walk model of word embeddings proposed by Arora et al., 2016 for KGEs to derive a scoring function that evaluates the strength of a relation r between two entities h (head) and t (tail) using their embeddings.

Prerequisites

The implementation of the RelWalk is built upon OpenKE that is implemented with TensorFlow. The code in this project requires:

 - python 
 - tensorflow

Pre-trained RelWalk Embeddings

To read the embeddings, use Read_Embeddings.py script in this repository.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published