dalinvip/cw2vec

cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information

49
/ 100
Emerging

This tool helps researchers and linguists analyze large volumes of Chinese text by generating numerical representations (embeddings) of words. You provide a text corpus in simplified Chinese, and it outputs word vectors that capture semantic relationships, which are useful for tasks like similarity analysis. It's designed for anyone working with Chinese language processing and understanding word meanings in context.

274 stars. No commits in the last 6 months.

Use this if you need to create high-quality word embeddings for Chinese text, particularly if you want to leverage stroke-level information to improve how words are represented.

Not ideal if you are working with languages other than Chinese or if you do not have computational linguistics experience, as it requires some technical setup.

Chinese-language-processing computational-linguistics text-analysis natural-language-understanding semantic-similarity
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

274

Forks

66

Language

C++

License

Apache-2.0

Last pushed

Mar 20, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/dalinvip/cw2vec"

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