babylonhealth/fastText_multilingual
Multilingual word vectors in 78 languages
This project helps anyone working with multilingual text by enabling direct comparison of word meanings across 78 different languages. You input word vectors for various languages, and it provides aligned word vectors where translations of words have similar numerical representations. This is useful for researchers and data scientists who need to understand semantic relationships between words across different languages.
1,202 stars. No commits in the last 6 months.
Use this if you need to compare the similarity of words or phrases across different languages and want to use numerical word representations to do so.
Not ideal if you only work with a single language or need to analyze the internal structure of words within a single language.
Stars
1,202
Forks
120
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Mar 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/babylonhealth/fastText_multilingual"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/similarities
Similarities: a toolkit for similarity calculation and semantic search....
explosion/sense2vec
🦆 Contextually-keyed word vectors
chakki-works/chakin
Simple downloader for pre-trained word vectors
sebischair/Lbl2Vec
Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with...
pdrm83/sent2vec
How to encode sentences in a high-dimensional vector space, a.k.a., sentence embedding.