five

Babelscape/story-summeval

收藏
Hugging Face2024-08-25 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/Babelscape/story-summeval
下载链接
链接失效反馈
官方服务:
资源简介:
--- language: - en license: - cc-by-nc-sa-4.0 pretty_name: Story SummEval size_categories: - n<1K --- # Dataset Card for Story-SummEval ## Dataset Description For a thorough description of the data creation please refer to the ACL 2024 paper: "FENICE: Factuality Evaluation of summarization based on NLI and Claim Extraction", Scirè et al. (2024). ### Summary This dataset contains summaries of stories from Gutenberg and Wikisource along with their factuality labels. Summaries are generated from several models provided by the paper "Echoes from Alexandria" by Scirè et al. (2023). ### Composition - **Number of (summary, label) pairs**: 319 - **Sources**: - Gutenberg - Wikisource ### Dataset Structure Each entry in the dataset includes: - `summary`: The summary of the story. - `label`: The factuality label of the summary. - `text_id`: Identifier for the original story text. - `source`: The source of the story text (either 'gutenberg' or 'wikisource'). To retrieve the story texts: - If the source is 'gutenberg', match the `text_id` value with the `id` column in the [manu/project_gutenberg](https://huggingface.co/datasets/manu/project_gutenberg) dataset using the 'en' split. - If the source is 'wikisource', match the `text_id` value with the `title` column in the [wikimedia/wikisource](https://huggingface.co/datasets/wikimedia/wikisource) dataset using the '20231201.en' split. ## Citation Information ```bibtex @inproceedings{scire-etal-2024-fenice, title = "{FENICE}: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction", author = "Scir{\`e}, Alessandro and Ghonim, Karim and Navigli, Roberto", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Findings of the Association for Computational Linguistics ACL 2024", month = aug, year = "2024", address = "Bangkok, Thailand and virtual meeting", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.findings-acl.841", pages = "14148--14161", } ```
提供机构:
Babelscape
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作