vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
This tool helps researchers and analysts compare how word meanings evolve across different collections of text, such as news articles from different years or specialized documents from distinct fields. You provide multiple text corpora and a combined 'compass' corpus, and it outputs aligned word embeddings. This allows you to directly compare word meanings and identify semantic shifts across your different text sources.
No commits in the last 6 months. Available on PyPI.
Use this if you need to understand how specific words or concepts change in meaning or association over time, across different topics, or in varied cultural contexts.
Not ideal if you only have a single text corpus and are not interested in comparing semantic changes across multiple datasets.
Stars
42
Forks
9
Language
Python
License
MIT
Category
Last pushed
Dec 26, 2022
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...
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...
ina-foss/twembeddings
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and...