RuMedBench

该数据集是一个针对俄语医学语言理解的基准，涵盖了包括文本分类、问题回答、自然语言推理以及命名实体识别等多种任务。它还在各种生物医学文本挖掘任务中展现了最先进的结果。该数据集的任务主要集中在医学语言理解任务上。

This dataset serves as a benchmark for Russian medical language understanding, encompassing a diverse range of tasks including text classification, question answering, natural language inference, and named entity recognition. It has also attained state-of-the-art performance across various biomedical text mining tasks. The tasks within this dataset are primarily centered around medical language understanding.