allenai/multixscience_sparse_max

---
annotations_creators:
- found
language_creators:
- found
language:
- en
license:
- unknown
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- summarization
paperswithcode_id: multi-xscience
pretty_name: Multi-XScience
---

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dataset, except the input source documents of its `test` split have been replaced by a __sparse__ retriever.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__: `"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==20`

Retrieval results on the `train` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.5482 | 0.2243 | 0.0547 | 0.4063 |

Retrieval results on the `validation` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.5476 | 0.2209 | 0.0553 | 0.4026 |

Retrieval results on the `test` set:

| Recall@100 | Rprec | Precision@k | Recall@k |
| ----------- | ----------- | ----------- | ----------- |
| 0.5480 | 0.2272 | 0.055 | 0.4039 |

原始信息汇总

数据集概述

基本信息

• 语言: 英语 (en)
• 许可证: 未知
• 多语言性: 单语
• 大小: 10K<n<100K
• 来源: 原始数据集
• 任务类别: 摘要生成
• 数据集名称: Multi-XScience
• 论文代码链接: multi-xscience

数据处理

• 测试集变更: 输入源文档被替换为稀疏检索器
• 检索流程:
  • 查询: 每个示例的related_work字段
  • 语料库: train, validation 和 test 分割中所有文档的并集
  • 检索器: BM25，使用PyTerrier库，默认设置
  • top-k策略: "max"，检索文档数k设置为数据集中示例间最大文档数，此处k==20

检索结果

• 训练集:

  • Recall@100: 0.5482
  • Rprec: 0.2243
  • Precision@k: 0.0547
  • Recall@k: 0.4063

• 验证集:

  • Recall@100: 0.5476
  • Rprec: 0.2209
  • Precision@k: 0.0553
  • Recall@k: 0.4026

• 测试集:

  • Recall@100: 0.5480
  • Rprec: 0.2272
  • Precision@k: 0.055
  • Recall@k: 0.4039