IntuitionEngineeringTeam/chars2vec

Character-based word embeddings model based on RNN for handling real world texts

56
/ 100
Established

This helps developers working with natural language by converting words into numerical vectors, even if those words contain typos, slang, or abbreviations. You provide a list of words, and it outputs numerical representations that capture how similar words are based on their characters. It's ideal for developers building systems that need to understand text data with real-world imperfections.

174 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to process text that frequently contains spelling errors, informal language, or custom abbreviations, and standard word embedding models struggle.

Not ideal if your text data is perfectly clean and grammatically correct, as simpler word embedding models might suffice.

natural-language-processing text-analytics information-retrieval search-algorithms data-preprocessing
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

174

Forks

39

Language

Python

License

Apache-2.0

Last pushed

Oct 09, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/IntuitionEngineeringTeam/chars2vec"

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