CVD
收藏arXiv2025-09-30 收录
下载链接:
https://huggingface.co/datasets/lhallee/abstract_domain_cvd
下载链接
链接失效反馈官方服务:
资源简介:
该数据集被用于评估模型在生物医学领域识别相似或不同论文的能力。在此数据集上,模型的F1_max得分接近完美,达到了0.97。这项任务的目的是评估句子相似性。
This dataset is utilized to evaluate models' ability to recognize similar or dissimilar papers in the biomedical domain. On this dataset, models achieve a near-perfect F1_max score of 0.97. The objective of this task is to assess sentence similarity.
提供机构:
Hugging Face



