search

CBLUEbenchmark / CBLUE

中文医疗信息处理基准CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark
https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414&lang=en-us
Apache License 2.0
727 stars 128 forks source link

请问排行榜上的CMeIE-V2 f1结果是RE任务的呢？还是端到端评测的呢？ #11

Closed QiQingY closed 1 year ago

flow3rdown commented 1 year ago

您好，会对预测的SPO结果（包括"subject", "predicate", "object"3个字段）和测试集标注结果进行精准匹配，具体细节请参考https://tianchi.aliyun.com/dataset/95414

QiQingY commented 1 year ago

所以就是针对一条样本，假设我预测的结果是[(s1,p1,o1), (s2,p2,o2)]，而标注结果是 [(s1,p1,o1)]，那么precision就是1/2，recall是1/1，对吗？

flow3rdown commented 1 year ago

对的，最终会用Micro-F1进行评估