AIbase
EN
Home
Jina Embeddings V2 Base Zh
J

Jina Embeddings V2 Base Zh

Developed by silverjam
Jina Embeddings V2 Base is a sentence embedding model optimized for Chinese, which can convert text into high-dimensional vector representations for calculating sentence similarity and feature extraction.
Text Embedding Supports Multiple LanguagesOpen Source License:Apache-2.0#Chinese sentence embedding#Semantic similarity calculation#Medical Q&A re-ranking
Downloads 63
Release Time : 6/5/2024

Model Overview

This model focuses on the embedding representation of Chinese text and supports various natural language processing tasks, such as sentence similarity calculation, text classification, and clustering.

Model Features

Optimized for Chinese
Specifically optimized for Chinese text to provide more accurate Chinese sentence embedding representations.
Multi-task support
Supports various natural language processing tasks, including sentence similarity calculation, text classification, and clustering.
High performance
Performs excellently in multiple Chinese benchmark tests, especially in the sentence similarity task.

Model Capabilities

Sentence embedding generation
Text feature extraction
Sentence similarity calculation
Text classification
Text clustering
Information retrieval

Use Cases

Information retrieval
Medical Q&A retrieval
Used for retrieving relevant questions and answers in a medical Q&A system
Performs well on the CMedQA dataset, with a MAP of 83.74
Text similarity
Q&A pair matching
Determine the relevance between questions and answers
The Pearson value of cosine similarity on the AFQMC dataset is 48.51
Text classification
Product review classification
Perform sentiment or topic classification on Chinese product reviews
Achieves an accuracy of 34.94% on the Amazon Chinese review classification task
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase