multixscience_sparse_oracle
收藏魔搭社区2025-08-29 更新2025-05-31 收录
下载链接:
https://modelscope.cn/datasets/allenai/multixscience_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 [Multi-XScience](https://huggingface.co/datasets/multi_x_science_sum) dataset, except the input source documents of its `test` split have been replaced by a __sparse__ retriever. The retrieval pipeline used:
- __query__: The `related_work` 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 |
| ----------- | ----------- | ----------- | ----------- |
| 0.5482 | 0.2243 | 0.2243 | 0.2243 |
Retrieval results on the `validation` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.5476 | 0.2209 | 0.2209 | 0.2209 |
Retrieval results on the `test` set:
| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.5480 | 0.2272 | 0.2272 | 0.2272 |
本数据集为[Multi-XScience](https://huggingface.co/datasets/multi_x_science_sum)数据集的副本,仅将其`test`子集的输入源文档替换为**稀疏检索器(sparse retriever)**。所采用的检索流程如下:
- **查询(query)**:每个样本的`related_work`字段
- **语料库(corpus)**:`train`训练子集、`validation`验证子集与`test`测试子集内所有文档的并集
- **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"`,即检索返回的文档数`k`设置为每个样本的原始输入文档数量
训练集检索指标如下:
| 召回率@100(Recall@100) | R精度(Rprec) | 精确率@k(Precision@k) | 召回率@k(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.5482 | 0.2243 | 0.2243 | 0.2243 |
验证集检索指标如下:
| 召回率@100(Recall@100) | R精度(Rprec) | 精确率@k(Precision@k) | 召回率@k(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.5476 | 0.2209 | 0.2209 | 0.2209 |
测试集检索指标如下:
| 召回率@100(Recall@100) | R精度(Rprec) | 精确率@k(Precision@k) | 召回率@k(Recall@k) |
| ----------- | ----------- | ----------- | ----------- |
| 0.5480 | 0.2272 | 0.2272 | 0.2272 |
提供机构:
maas创建时间:
2025-05-27
搜集汇总
数据集介绍

背景与挑战
背景概述
该数据集是Multi-XScience的一个变体,其测试集的输入文档被替换为通过BM25稀疏检索器获取的结果,检索时使用'related_work'字段作为查询并采用'oracle'策略。在训练、验证和测试集上,检索性能指标如Recall@100均约为0.55,Precision@k约为0.22。
以上内容由遇见数据集搜集并总结生成



