The optimization testing set and the generalization evaluation set. The optimization testing set consists of a randomly selected 20 percent subset of the training data (501 case reports and 3000 sets of synthetic sentences), while the generalization evaluation set is an entirely separate subset from the case report cohort, including 208 case reports and 3000 sets of synthetic sentences. OVO denotes One vs. One macro AUC scores. BERT is the Base Uncased model.
收藏NIAID Data Ecosystem2026-05-02 收录
下载链接：
https://figshare.com/articles/dataset/The_optimization_testing_set_and_the_generalization_evaluation_set_The_optimization_testing_set_consists_of_a_randomly_selected_20_percent_subset_of_the_training_data_501_case_reports_and_3000_sets_of_synthetic_sentences_while_the_generaliz/29463020
下载链接
链接失效反馈官方服务：
资源简介：
The optimization testing set and the generalization evaluation set. The optimization testing set consists of a randomly selected 20 percent subset of the training data (501 case reports and 3000 sets of synthetic sentences), while the generalization evaluation set is an entirely separate subset from the case report cohort, including 208 case reports and 3000 sets of synthetic sentences. OVO denotes One vs. One macro AUC scores. BERT is the Base Uncased model.
创建时间：
2025-07-02
