https://github.com/aksw/kg2vec
🏎 KG2Vec: Expeditious Generation of Knowledge Graph Embeddings
https://github.com/aksw/kg2vec
Last synced: 1 day ago
JSON representation
🏎 KG2Vec: Expeditious Generation of Knowledge Graph Embeddings
- Host: GitHub
- URL: https://github.com/aksw/kg2vec
- Owner: AKSW
- License: mit
- Created: 2018-03-21T15:23:12.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2023-03-24T23:44:37.000Z (about 3 years ago)
- Last Synced: 2025-09-09T02:26:54.338Z (9 months ago)
- Language: Python
- Homepage: http://tsoru.aksw.org/kg2vec/
- Size: 241 KB
- Stars: 29
- Watchers: 23
- Forks: 12
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# KG2Vec
🏎 KG2Vec: Expeditious Generation of Knowledge Graph Embeddings
## Usage
* Download data from http://tsoru.aksw.org/kg2vec/
```bash
sh kg2vec_.sh
```
### LSTM-based scoring function
```bash
sh kg2vec_lstm.sh aksw-bib aksw-bib.train+valid.nt 10 aksw-bib.test.nt output random 100
```
### Analogy-based scoring function
```bash
sh kg2vec_analogy.sh aksw-bib aksw-bib.train+valid.nt 10 aksw-bib.test.nt output
```
## Use cases
* An add-on for the [Genesis Linked Data browser](https://github.com/dice-group/GENESIS/tree/diesel) uses a low-dimensional KG2Vec model trained on DBpedia for retrieving similar resources.
## Cite
* Presented at the 5th European Conference on Data Analysis (ECDA 2018) as _"A Simple and Fast Approach to Knowledge Graph Embedding"_.
* Working paper: https://arxiv.org/abs/1803.07828
```bib
@proceedings{soru-kg2vec-2018,
author = "Tommaso Soru and Stefano Ruberto and Diego Moussallem and Edgard Marx and Diego Esteves and Axel-Cyrille {Ngonga Ngomo}",
title = "Expeditious Generation of Knowledge Graph Embeddings",
year = "2018",
}
```