vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
Employs a "compass" — a general embedding trained on concatenated corpora — to freeze word2vec's CBOW input layer, enabling efficient cross-corpora alignment without external dictionaries. Built on a custom gensim implementation, it detects semantic shifts across temporal, geographic, or topical text collections by making embeddings from different corpora directly comparable via cosine similarity.
No commits in the last 6 months. Available on PyPI.
Stars
42
Forks
9
Language
Python
License
MIT
Category
Last pushed
Dec 26, 2022
Monthly downloads
60
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/vinid/cade"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
ina-foss/twembeddings
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and...
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...