CBLUE2.0: A Chinese Biomedical Language Understanding Evaluation Benchmark

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、平安医疗科技、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。 <br /> 本数据集为CBLUE2.0版本，不再维护更新，请访问CBLUE评测基准官网获取最新版本：https://tianchi.aliyun.com/cblue ，或直接访问 https://tianchi.aliyun.com/dataset/95414 查看最新版本。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 (CIPS) under the principle of lawful open sharing. It is hosted by the Alibaba Cloud Tianchi Platform, and co-organized by multiple institutions conducting smart medical research, including Yidu Cloud (Beijing) Technology Co., Ltd., Ping An Medical Technology, Quark, Peking University, Zhengzhou University, Peng Cheng Laboratory, Harbin Institute of Technology (Shenzhen), Tongji University, etc. The initiative aims to promote the development of Chinese medical NLP technologies and their related communities. This dataset corresponds to the CBLUE 2.0 version, which is no longer maintained or updated. Please visit the official website of the CBLUE evaluation benchmark for the latest version: https://tianchi.aliyun.com/cblue, or directly access https://tianchi.aliyun.com/dataset/95414 to view the latest release.

搜集汇总

背景与挑战

背景概述

CBLUE2.0是一个中文医学语言理解评估基准，由中国中文信息学会医疗健康与生物信息处理专业委员会发起，阿里云天池平台承办，并联合多家机构协办，旨在促进中文医学NLP领域的发展。该数据集涵盖医学文本信息抽取、医学术语标准化、医学文本分类、医学句子语义关系判定和医学对话理解与生成等5大类任务共14个子任务。需要注意的是，这是2.0版本且已停止更新，建议用户访问官方渠道获取最新版本。