cnclabs/ICE

ICE: Item Concept Embedding

28
/ 100
Experimental

This toolkit helps you understand the conceptual similarity between items, like songs or movies, based on their descriptive text. You provide text describing various items and their associated concepts (keywords), and it generates numerical representations (embeddings) that allow you to find items or concepts that are conceptually similar, even if they are different types of entities. This is useful for data scientists, product managers, or content strategists looking to improve recommendation systems or content organization.

No commits in the last 6 months.

Use this if you need to compare different types of items (e.g., songs and artists, products and features) based on their underlying conceptual meaning derived from textual descriptions.

Not ideal if your items lack significant textual information for conceptual comparison or if you only need exact keyword matching.

recommendation-systems content-discovery information-retrieval semantic-search data-mining
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

89

Forks

8

Language

C++

License

Last pushed

Nov 25, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/cnclabs/ICE"

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