uhh-lt/path2vec

Learning to represent shortest paths and other graph-based measures of node similarities with graph embeddings

41
/ 100
Emerging

Need to quickly calculate how similar concepts are based on their relationships in a complex network, like a dictionary or knowledge graph? This tool helps you transform those complex relationships into simple numerical representations. You input a network with connections between terms, and it provides fast, numerical 'scores' of how related any two terms are. This is useful for computational linguists, semantic engineers, or anyone working with large-scale semantic networks for tasks like analyzing word meanings.

No commits in the last 6 months.

Use this if you need to rapidly estimate how semantically similar words or concepts are, based on their connections in a structured knowledge base like WordNet, without the slow computation of direct pathfinding.

Not ideal if your primary goal is to visualize or directly analyze the raw graph structure itself, rather than derive numerical similarity scores.

computational-linguistics natural-language-processing semantic-similarity knowledge-graphs word-sense-disambiguation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

33

Forks

13

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Aug 27, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/uhh-lt/path2vec"

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