illuin-conteb/squad-conteb-train
收藏Hugging Face2025-06-02 更新2025-10-18 收录
下载链接：
https://hf-mirror.com/datasets/illuin-conteb/squad-conteb-train
下载链接
链接失效反馈官方服务：
资源简介：
ConTEB - SQuAD数据集是ConTEB（Context-aware Text Embedding Benchmark）的一部分，旨在评估上下文嵌入模型的性能。它基于广泛使用的SQuAD数据集，包含原始文档、从这些文档中提取的文本块和查询。该数据集为上下文化嵌入提供了一个专注的基准，包含48个文档、1619个文本块和8501个查询。
The ConTEB - SQuAD dataset is part of the ConTEB (Context-aware Text Embedding Benchmark), designed to evaluate the capabilities of contextual embedding models. It is based on the widely used SQuAD dataset and includes original documents, text chunks extracted from these documents, and queries. This dataset provides a focused benchmark for contextualized embeddings, containing 48 documents, 1619 chunks, and 8501 queries.
提供机构：
illuin-conteb
