CBLUE 4.0

中文医疗信息处理挑战榜CBLUE(Chinese Biomedical Language Understanding Evaluation)是中国中文信息学会医疗健康与生物信息处理专业委员会在合法开放共享的理念下发起，由阿里云天池平台承办，并由医渡云（北京）技术有限公司、腾讯天衍实验室、平安医疗科技、阿里夸克、北京大学、郑州大学、鹏城实验室、哈尔滨工业大学(深圳）、同济大学、中山大学、复旦大学、华东师范大学等开展智慧医疗研究的单位共同协办，旨在推动中文医学NLP技术和社区的发展。
官网地址： https://tianchi.aliyun.com/cblue
论文： https://arxiv.org/pdf/2106.08087.pdf
Github: https://github.com/CBLUEbenchmark/CBLUE

The Chinese Biomedical Language Understanding Evaluation (CBLUE) Challenge Benchmark was initiated by the Professional Committee on Medical Health and Bioinformatics Processing of the Chinese Information Processing Society of China under the concept of lawful open sharing. It is hosted by Alibaba Cloud Tianchi Platform and co-organized by multiple institutions engaged in smart healthcare research, including Yidu Cloud (Beijing) Technology Co., Ltd., Tencent Tianyan Lab, Ping An Medical Technology, Alibaba Quark, Peking University, Zhengzhou University, Peng Cheng Laboratory, Harbin Institute of Technology (Shenzhen), Tongji University, Sun Yat-sen University, Fudan University, East China Normal University, etc. It aims to promote the development of Chinese medical natural language processing (NLP) technology and its community.
Official website: https://tianchi.aliyun.com/cblue
Paper: https://arxiv.org/pdf/2106.08087.pdf
Github: https://github.com/CBLUEbenchmark/CBLUE

搜集汇总

背景与挑战

背景概述

CBLUE 4.0是一个中文生物医学语言理解评估基准数据集，旨在推动中文医学自然语言处理技术发展。该数据集由多个机构协办，覆盖医学文本信息抽取、分类、语义关系判定、生成和检索等多类任务，共包含多个子数据集，如CHIP-CDEE、CMeEE-V2等。作为CBLUE系列的第四版，它在之前版本基础上新增了10个任务，进一步丰富了语料来源和任务难度，适用于医疗AI领域的研究和评测。