clips/beir-nl-climate-fever

BEIR-NL是一个荷兰语版本的BEIR基准测试，涵盖了从生物医学、金融文本到一般网络内容的各种领域。数据集包含多个任务，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。数据集结构包括corpus、queries和qrels文件，分别用于存储文档、查询和查询文档相关性判断。数据集创建的目的是为了促进荷兰语信息检索模型的发展，通过自动翻译BEIR数据集来实现。然而，数据集存在一些局限性，如缺乏原生荷兰语资源、数据污染问题以及基准测试的有效性随时间推移可能降低。

BEIR-NL is a Dutch-translated version of the BEIR benchmark, containing datasets from various domains and tasks such as fact-checking, question-answering, and biomedical information retrieval. The dataset structure includes a corpus, queries, and relevance judgment files, all adhering to the BEIR benchmarks structure. The creation of 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 linguistic and cultural complexities of Dutch.