wcep_sparse_oracle
收藏魔搭社区2025-08-22 更新2025-05-31 收录
下载链接:
https://modelscope.cn/datasets/allenai/wcep_sparse_oracle
下载链接
链接失效反馈官方服务:
资源简介:
This is a copy of the [WCEP-10](https://huggingface.co/datasets/ccdv/WCEP-10) dataset, except the input source documents of its `test` split have been replaced by a __sparse__ retriever.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__: `"oracle"`, i.e. the number of documents retrieved, `k`, is set as the original number of input documents for each example
Retrieval results on the `train` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8753 | 0.6443 | 0.6443 | 0.6443 |
Retrieval results on the `validation` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8706 | 0.6280 | 0.6280 | 0.6280 |
Retrieval results on the `test` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8836 | 0.6658 | 0.6658 | 0.6658 |
本数据集为[WCEP-10](https://huggingface.co/datasets/ccdv/WCEP-10)的副本,仅将其`test`划分的输入源文档替换为**稀疏检索器(sparse retriever)**获取的结果。所采用的检索流水线(retrieval pipeline)如下:
- **查询(query)**:每个样本的`summary`字段
- **语料库(corpus)**:`train`、`validation`与`test`划分中所有文档的并集
- **检索器(retriever)**:基于[PyTerrier](https://pyterrier.readthedocs.io/en/latest/)实现的BM25检索器,采用默认配置
- **Top-k策略(top-k strategy)**:`"oracle"`,即检索文档数`k`设置为每个样本原始输入文档的数量
训练集检索结果:
| 召回率@100(Recall@100) | R精度(Rprec) | 精确率@k(Precision@k) | 召回率@k(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.8753 | 0.6443 | 0.6443 | 0.6443 |
验证集检索结果:
| 召回率@100(Recall@100) | R精度(Rprec) | 精确率@k(Precision@k) | 召回率@k(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.8706 | 0.6280 | 0.6280 | 0.6280 |
测试集检索结果:
| 召回率@100(Recall@100) | R精度(Rprec) | 精确率@k(Precision@k) | 召回率@k(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.8836 | 0.6658 | 0.6658 | 0.6658 |
提供机构:
maas
创建时间:
2025-05-28



