clips/beir-nl-scidocs

BEIR-NL是BEIR基准测试的荷兰语翻译版本，是一个多样化和异构的数据集集合，涵盖了从生物医学和金融文本到一般网络内容的各种领域。BEIR-NL包含多个任务，如事实核查、问答、生物医学信息检索、论点检索、重复问题检索、引用预测和实体检索。该数据集旨在通过将公开的BEIR数据集自动翻译成荷兰语，促进荷兰语信息检索模型的发展。

BEIR-NL is a Dutch-translated version of the BEIR benchmark, containing datasets from various domains, covering tasks such as fact-checking, question-answering, and biomedical information retrieval. The dataset includes a corpus (document set), queries (query set), and qrels (relevance judgment file), each with specific formats and fields. BEIR-NL aims to promote the development of Dutch information retrieval models, although it relies on data translated from English, which may not fully reflect the semantics and cultural context of Dutch.