cochrane_sparse_mean

This is a copy of the [Cochrane](https://huggingface.co/datasets/allenai/mslr2022) dataset, except the input source documents of its `validation` split have been replaced by a __sparse__ retriever. The retrieval pipeline used:

- __query__: The `target` field of each example
- __corpus__: The union of all documents in the `train`, `validation` and `test` splits. A document is the concatenation of the `title` and `abstract`.
- __retriever__: BM25 via [PyTerrier](https://pyterrier.readthedocs.io/en/latest/) with default settings
- __top-k strategy__: `"mean"`, i.e. the number of documents retrieved, `k`, is set as the mean number of documents seen across examples in this dataset, in this case `k==9`

Retrieval results on the `train` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.7014 | 0.3841 | 0.2976 | 0.4157 |

Retrieval results on the `validation` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.7226 | 0.4023 | 0.3095 | 0.4443 |

Retrieval results on the `test` set:

N/A. Test set is blind so we do not have any queries.

本数据集为[Cochrane](https://huggingface.co/datasets/allenai/mslr2022)的复刻版本，仅将其`validation`（验证）划分的输入源文档替换为**稀疏检索器（sparse retriever）**获取的结果。所采用的检索流程如下：
- **查询（query）**：每个示例的`target`（目标）字段
- **语料库（corpus）**：`train`（训练）、`validation`（验证）与`test`（测试）划分的全部文档的并集；单篇文档由`title`（标题）与`abstract`（摘要）拼接而成
- **检索器（retriever）**：采用默认参数、基于[PyTerrier](https://pyterrier.readthedocs.io/en/latest/)实现的BM25检索器
- **top-k策略**：采用"均值（mean）"策略，即检索文档数`k`设置为该数据集所有示例中平均出现的文档数，此处`k=9`

训练集检索结果：
| 召回率@100 | R准确率（Rprec） | 精确率@k | 召回率@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.7014 | 0.3841 | 0.2976 | 0.4157 |

验证集检索结果：
| 召回率@100 | R准确率（Rprec） | 精确率@k | 召回率@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.7226 | 0.4023 | 0.3095 | 0.4443 |

测试集检索结果：
N/A。由于测试集为盲集，故无可用查询。