yannvgn/laserembeddings

LASER multilingual sentence embeddings as a pip package

52
/ 100
Established

This project helps anyone working with text across multiple languages who needs to compare or categorize sentences. It takes sentences in various languages as input and converts them into universal numerical codes (embeddings). These codes allow you to identify similar sentences, regardless of their original language, making it useful for researchers, analysts, or anyone building language-agnostic text applications.

224 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Use this if you need to understand the semantic similarity between sentences written in different languages without having to translate them first.

Not ideal if you need to train or fine-tune the model for very specific domain-specific language tasks, as the pre-trained models are not designed for further training.

multilingual-text-analysis cross-lingual-information-retrieval natural-language-processing text-categorization semantic-search
Stale 6m
Maintenance 0 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

224

Forks

29

Language

Python

License

BSD-3-Clause

Last pushed

Aug 11, 2023

Commits (30d)

0

Dependencies

5

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yannvgn/laserembeddings"

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