explosion/sense2vec

🦆 Contextually-keyed word vectors

60
/ 100
Established

Disambiguates word vectors using part-of-speech tags and entity labels to represent multi-word phrases as distinct senses (e.g., "natural_language_processing|NOUN" vs "natural|ADJ"). Integrates as a spaCy v3 pipeline component with extension attributes for vector lookup and nearest-neighbor queries, plus optional neighbor caching for performance. Supports training custom vectors from raw text using pretrained spaCy models combined with GloVe or fastText embeddings.

1,672 stars and 4,793 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 18 / 25
Maturity 18 / 25
Community 22 / 25

How are scores calculated?

Stars

1,672

Forks

239

Language

Python

License

MIT

Last pushed

Apr 23, 2025

Monthly downloads

4,793

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/explosion/sense2vec"

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