KwangKa/SIMCSE_unsup

中文无监督SimCSE Pytorch实现

46
/ 100
Emerging

This tool helps data scientists, AI engineers, and NLP specialists improve how computers understand the meaning of Chinese sentences. It takes a collection of Chinese text and learns to represent each sentence as a numerical code (an embedding), which can then be used to find other sentences with similar meanings or evaluate semantic understanding. This is useful for building applications that require deep comprehension of Chinese language nuances.

135 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, context-aware numerical representations (embeddings) for Chinese sentences without labeled data, especially for tasks like semantic search or text similarity.

Not ideal if your primary need is for non-Chinese languages or if you specifically require a supervised learning approach with extensive labeled data for sentence embeddings.

natural-language-processing chinese-text-analysis semantic-search information-retrieval text-similarity
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

135

Forks

30

Language

Python

License

MIT

Last pushed

Jul 08, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/KwangKa/SIMCSE_unsup"

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