# explosion/sense2vec

🦆 Contextually-keyed word vectors

Repository: https://github.com/explosion/sense2vec
Canonical: https://ross.abutalabs.com/products/sense2vec
Homepage: https://explosion.ai/blog/sense2vec-reloaded
Language: Python
License: MIT
License Family: permissive
Topics: spacy, nlp, natural-language-processing, word2vec, python, sense2vec, gensim, gensim-word2vec, machine-learning
Last push: 2026-03-27T08:50:56+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 8, longevity 100
- inputs: {"age_days": 3875, "days_push": 159, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1679, forks 236 (observed 2026-08-28T04:05:21.405208+00:00)

## What it is
A Python library implementing sense2vec, contextually-keyed word vectors that learn embeddings for multi-word phrases and part-of-speech-disambiguated senses. It integrates as a spaCy pipeline component and supports training custom vectors with GloVe or fastText.

## Use cases
- find similar multi-word phrases like natural language processing
- query word vectors disambiguated by part of speech
- train contextually-keyed word vectors on my own text corpus
- add sense2vec vectors to a spaCy pipeline
- bootstrap named entity recognition lists from similar phrases
- compute semantic similarity between entity phrases

## When to choose
- you already use spaCy and want phrase-level or sense-aware embeddings
- you need vectors for multi-word expressions and named entities
- you want to generate similar-phrase lists for rule-based NER patterns

## When to avoid
- you need modern contextual transformer embeddings rather than static word vectors
- you need general-purpose sentence or document embeddings
- you don't use spaCy and only need plain word2vec

## Facets
- artifact type: library
- maturity: stable
- function: nlp, machine-learning, serialization
- domain: machine-learning
- platform: python
- tags: word-vectors, sense2vec, word2vec, embeddings, spacy, named-entity-recognition, semantic-similarity, natural-language-processing

## Member repositories
- explosion/sense2vec (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:21.405208+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:41:30.807094+00:00, confidence not recorded.
  - readme: https://github.com/explosion/sense2vec (fetched 2026-08-28T04:05:21.405208+00:00, sha c31cd49ec31a)
  - homepage: https://explosion.ai/blog/sense2vec-reloaded (fetched 2026-08-29T11:14:46.566915+00:00, sha bcc25e60ac26)
  - site_page: https://explosion.ai/about (fetched 2026-08-29T11:14:46.576555+00:00, sha cc9d936cdc5c)
  - registry_pypi: https://pypi.org/pypi/sense2vec/json (fetched 2026-08-29T11:14:46.579039+00:00, sha d4d5627fc80a)
- Data as of 2026-08-30T08:39:29.467469+00:00.