soda-inria/ken_embeddings

KEN: Relational Data Embeddings

31
/ 100
Emerging

This project helps data scientists and analysts enrich their datasets by providing pre-computed, comprehensive background information on common real-world entities like cities, companies, and people. You input a list of these entities, and it outputs a numerical vector (an 'embedding') for each, summarizing details from sources like Wikipedia. This saves significant manual effort in gathering and structuring external data to improve predictive models.

No commits in the last 6 months.

Use this if you need to quickly add rich, relevant background information to your datasets for entities such as cities, companies, or people to improve the accuracy of your predictive models without tedious manual feature engineering.

Not ideal if your dataset primarily consists of highly specialized or niche entities not commonly found or well-documented in general knowledge bases like Wikipedia.

data-enrichment predictive-modeling feature-engineering knowledge-graphs entity-resolution
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

34

Forks

3

Language

Python

License

CC-BY-4.0

Last pushed

Jan 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/soda-inria/ken_embeddings"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.