GermanSTSBenchmark

该数据集是一个针对德语文本相似度评估的基准测试集，常用于评价句子对之间的相似度。它特别适用于评估双语模型在德语任务上的性能表现，其任务类型为语义文本相似度。This dataset is a benchmark dataset for German text similarity evaluation, commonly used to evaluate the similarity between sentence pairs. It is particularly well-suited for assessing the performance of bilingual models on German-language tasks, targeting the Semantic Textual Similarity task.