mteb/JinaVDRAirbnbSyntheticRetrieval

JinaVDRAirbnbSyntheticRetrieval是一个多语言视觉文档检索数据集，包含阿拉伯语、德语、英语、法语、印地语、匈牙利语、日语、俄语、西班牙语和中文的图像和文本信息。数据集分为corpus、qrels和queries三个部分，分别用于图像-文本检索、查询-文档相关性和查询文本。每个部分都有测试集，并提供了文件大小和示例数量等信息。JinaVDRAirbnbSyntheticRetrieval is a multilingual visual-document retrieval dataset that includes image and text information in Arabic, German, English, French, Hindi, Hungarian, Japanese, Russian, Spanish, and Chinese. The dataset is divided into three main parts: corpus, qrels, and queries, used for image-text retrieval, query-document relevance, and query text respectively. Each part has a test set with file size and number of examples provided.