KwangKa/SIMCSE_unsup
中文无监督SimCSE Pytorch实现
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.
Stars
135
Forks
30
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...