multinews_sparse_max
收藏魔搭社区2025-07-11 更新2025-05-31 收录
下载链接:
https://modelscope.cn/datasets/allenai/multinews_sparse_max
下载链接
链接失效反馈官方服务:
资源简介:
This is a copy of the [Multi-News](https://huggingface.co/datasets/multi_news) dataset, except the input source documents of its `test` split have been replaced by a __sparse__ retriever. The retrieval pipeline used:
- __query__: The `summary` field of each example
- __corpus__: The union of all documents in the `train`, `validation` and `test` splits
- __retriever__: BM25 via [PyTerrier](https://pyterrier.readthedocs.io/en/latest/) with default settings
- __top-k strategy__: `"max"`, i.e. the number of documents retrieved, `k`, is set as the maximum number of documents seen across examples in this dataset, in this case `k==10`
Retrieval results on the `train` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8793 | 0.7460 | 0.2213 | 0.8264 |
Retrieval results on the `validation` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8748 | 0.7453 | 0.2173 | 0.8232 |
Retrieval results on the `test` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8775 | 0.7480 | 0.2187 | 0.8250 |
本数据集为[Multi-News](https://huggingface.co/datasets/multi_news)数据集的复刻版本,仅其测试(test)划分的输入源文档已由**稀疏检索器(sparse retriever)**检索得到的结果完成替换。所采用的检索流程如下:
- **查询(query)**:每个样本的`摘要(summary)`字段
- **语料库(corpus)**:训练(train)、验证(validation)与测试(test)划分下全部文档的并集
- **检索器(retriever)**:基于[PyTerrier](https://pyterrier.readthedocs.io/en/latest/)实现的BM25算法,采用默认参数配置
- **Top-k策略**:采用`"max"`模式,即检索文档数`k`被设定为该数据集所有样本中出现的最大文档数,本次场景下`k=10`
训练集检索性能如下:
| 100召回率(Recall@100) | R-精度(Rprec) | k精度(Precision@k) | k召回率(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.8793 | 0.7460 | 0.2213 | 0.8264 |
验证集检索性能如下:
| 100召回率(Recall@100) | R-精度(Rprec) | k精度(Precision@k) | k召回率(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.8748 | 0.7453 | 0.2173 | 0.8232 |
测试集检索性能如下:
| 100召回率(Recall@100) | R-精度(Rprec) | k精度(Precision@k) | k召回率(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.8775 | 0.7480 | 0.2187 | 0.8250 |
提供机构:
maas
创建时间:
2025-05-27



