AIbase
EN
Home
Yinka
Y

Yinka

Developed by Classical
This model has been evaluated on multiple tasks in the Chinese Text Embedding Benchmark (MTEB), including text similarity, classification, clustering, and retrieval tasks.
Large Language Model
Transformers
#Chinese Semantic Similarity#Multi-task Evaluation#Medical Retrieval Optimization
Downloads 388
Release Time : 5/30/2024

Model Overview

This is a model evaluated on the Chinese Text Embedding Benchmark (MTEB), supporting various natural language processing tasks such as semantic similarity calculation, text classification, clustering, and information retrieval.

Model Features

Multi-task Evaluation
Comprehensively evaluated on multiple tasks of the MTEB Chinese benchmark, including STS, classification, clustering, and retrieval.
Chinese Optimization
Specifically optimized for Chinese text processing, performing well on multiple Chinese datasets.
Diverse Metrics
Provides various evaluation metrics, including Pearson correlation coefficient, Spearman correlation coefficient, accuracy, F1 score, etc.

Model Capabilities

Text similarity calculation
Text classification
Text clustering
Information retrieval
Semantic matching
Question-answer reranking

Use Cases

E-commerce
Product Review Classification
Sentiment classification of product reviews on e-commerce platforms
Achieved 88.48% accuracy on the JDReview dataset
Product Retrieval
Product search and recommendation on e-commerce platforms
Achieved MAP@10 of 63.11 on the EcomRetrieval dataset
Healthcare
Medical Q&A Retrieval
Retrieval and matching of medical domain questions
Achieved MAP of 89.26 and 90.05 on the CMedQAv1 and CMedQAv2 datasets respectively
Medical Literature Retrieval
Retrieval and ranking of medical-related literature
Achieved NDCG@10 of 65.20 on the MedicalRetrieval dataset
General Semantic Understanding
Semantic Similarity Calculation
Calculate the semantic similarity between two texts
Achieved Pearson correlation coefficient of 73.68 on the LCQMC dataset
Text Classification
Multi-category classification of text
Achieved accuracy of 51.77% on the IFlyTek dataset
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