Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
xiaoxiong b4243c986c | 1 year ago | |
---|---|---|
README.md | 1 year ago |
DuReader yesno是一个以观点极性判断为目标任务的数据集,可以弥补抽取类数据集评测指标的缺陷,从而更好地评价模型对观点极性的理解能力。
DuReader_yesno数据集的任务定义如下:
对于一个给定的问题q、一系列相关文档D=d1, d2, …, dn,以及人工抽取答案段落摘要a,要求参评系统自动对问题q、候选文档D以及答案段落摘要a进行分析,输出每个答案段落摘要所表述的是非观点极性。其中,极性分为三类 {Yes, No, Depends}。其中:
Yes:肯定观点,肯定观点指的是答案给出了较为明确的肯定态度。有客观事实的从客观事实的角度出发,主观态度类的从答案的整体态度来判断。
No:否定观点,否定观点通常指的是答案较为明确的给出了与问题相反的态度。
Depends:无法确定/分情况,主要指的是事情本身存在多种情况,不同情况下对应的观点不一致;或者答案本身对问题表示不确定,要具体具体情况才能判断。
例如:
{
"documents": [
{
"title": "香蕉能放冰箱吗 香蕉剥皮冷冻保存_健康贴士_保健_99健康网",
"paragraphs": [
"本文导读:............."
]
}
],
"yesno_answer": "No",
"question": "香蕉能放冰箱吗",
"answer": "香蕉不能放冰箱,香蕉如果放冰箱里,会更容易变坏,会发黑腐烂。",
"id": 293
}
如在学术论文中使用该数据集,请添加相关引用说明,具体如下:
He, W., et al. (2018). DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications. Proceedings of the Workshop on Machine Reading for Question Answering, 37–46.
论文地址:https://aclanthology.org/W18-2605/
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》