数据资源Chinese biomedical and clinical textChinese biomedical NLP benchmark8 biomedical NLU tasks; see official repository开放访问

CBLUE：中文生物医学语言理解评测基准

CBLUE is a Chinese biomedical language understanding benchmark covering real-world biomedical NLP tasks such as named entity recognition, relation extraction, term normalization, clinical trial classification, sentence similarity, and medical question answering. It is useful for evaluating Chinese clinical NLP models and medical language models.

临床语言智能数据集 Chinese medical NLP benchmark information extraction QA

数据资源详情

数据模态: Chinese biomedical and clinical text
资源类别: Chinese biomedical NLP benchmark
数据规模: 8 biomedical NLU tasks; see official repository
许可协议: Dataset-specific terms; see official repository
访问方式: 开放访问
适用任务: named entity recognition、relation extraction、term normalization、medical text classification、sentence similarity、医学问答
来源: CBLUEbenchmark GitHub / CBLUE project