wcep_dense_max

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dataset, except the input source documents of its `test` split have been replaced by a __dense__ retriever.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__: [`facebook/contriever-msmarco`](https://huggingface.co/facebook/contriever-msmarco) 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 |
| ----------- | ----------- | ----------- | ----------- |
| 0.8590 | 0.6490 | 0.5967 | 0.6631 |

Retrieval results on the `validation` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8578 | 0.6326 | 0.6040 | 0.6401 |

Retrieval results on the `test` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8678 | 0.6631 | 0.6301 | 0.6740 |

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**密集型检索器（dense retriever）**。所采用的检索流程如下：
- **查询（query）**：每个样本的`summary`字段
- **语料库（corpus）**：`train`、`validation`与`test`划分下的全部文档的并集
- **检索器（retriever）**：通过[PyTerrier](https://pyterrier.readthedocs.io/en/latest/)以默认配置调用[`facebook/contriever-msmarco`](https://huggingface.co/facebook/contriever-msmarco)
- **top-k策略**：采用`"max"`策略，即检索文档数`k`被设置为该数据集所有样本中出现的最大文档数，此处`k=10`

训练集检索结果：
| 召回率@100 | Rprec | 精确率@k | 召回率@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8590 | 0.6490 | 0.5967 | 0.6631 |

验证集检索结果：
| 召回率@100 | Rprec | 精确率@k | 召回率@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8578 | 0.6326 | 0.6040 | 0.6401 |

测试集检索结果：
| 召回率@100 | Rprec | 精确率@k | 召回率@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.8678 | 0.6631 | 0.6301 | 0.6740 |

搜集汇总

背景与挑战

背景概述

该数据集基于WCEP-10数据集，通过密集检索器替换了测试集的输入源文档，检索过程使用摘要作为查询、全部分割文档作为语料库，并采用最大文档数策略（k=10）。在训练、验证和测试集上，检索性能指标如Recall@100和Precision@k均表现良好，例如测试集的Recall@100达到0.8678。