YC-wind/embedding_study
中文预训练模型生成字向量学习，测试BERT，ELMO的中文效果
This project helps developers evaluate and compare different word embedding models like BERT, ELMO, and Word2Vec for Chinese text. It takes Chinese text as input and generates numerical representations (embeddings) for words and sentences. Data scientists, NLP engineers, and researchers working with Chinese language processing would use this to understand which models perform best for their specific tasks.
100 stars. No commits in the last 6 months.
Use this if you are an NLP developer or researcher working with Chinese text and need to generate and compare word or sentence embeddings using established models.
Not ideal if you are looking for a ready-to-use, production-grade API for generating Chinese embeddings without diving into model code.
Stars
100
Forks
27
Language
Python
License
—
Category
Last pushed
Jan 22, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/YC-wind/embedding_study"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MinishLab/model2vec
Fast State-of-the-Art Static Embeddings
AnswerDotAI/ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
tensorflow/hub
A library for transfer learning by reusing parts of TensorFlow models.
Embedding/Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
twang2218/vocab-coverage
语言模型中文认知能力分析