%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Gte Base Zh
G
Gte Base Zh
Developed by thenlper
gte-base-zh is a general-purpose text embedding model optimized for Chinese, supporting various natural language processing tasks including semantic similarity calculation, text classification, information retrieval, etc.
Downloads 22.03k
Release Time : 11/8/2023
Model Overview
This model focuses on generating high-quality sentence embeddings, suitable for semantic understanding and representation of Chinese texts. It excels in multiple Chinese benchmark tests, particularly in semantic similarity and information retrieval tasks.
Model Features
Multi-task Support
Supports various natural language processing tasks, including semantic similarity calculation, text classification, information retrieval, etc.
Chinese Optimization
Specifically optimized for Chinese texts, demonstrating excellent performance in multiple Chinese benchmark tests.
Efficient Retrieval
Performs exceptionally well in information retrieval tasks, especially in medical domain question retrieval.
Model Capabilities
Semantic Text Similarity Calculation
Text Classification
Information Retrieval
Text Clustering
Re-ranking
Use Cases
Finance
Financial Question Matching
Used to match similar financial questions, such as tasks in the AFQMC dataset
Cosine similarity Pearson correlation coefficient reaches 44.46
Medical
Medical QA Retrieval
Used to retrieve answers related to medical questions
Achieves MAP scores of 86.79 and 87.20 on CMedQAv1 and CMedQAv2 datasets respectively
E-commerce
Product Review Classification
Classifies Chinese product reviews on Amazon
Accuracy reaches 45.82%
TransformersFeatured Recommended AI Models