Unverified50% confidenceFactExact time
word2vec负采样中，对每个正样本随机采样k个（通常5-20个）负样本，采样概率通常按词频的3/4次方分布
1
Sources
50%
Confidence
Long-term
Relevance
8/13/2026
First Seen
Sources
Related Claims
UnverifiedAUC equals the probability that, when one positive sample and one negative sample are randomly drawn from all positive and negative samples respectively, the predicted score of the positive sample is higher than that of the negative sample.71% similarUnverified置换检验通过大量随机置换（通常1000到10000次）构建零假设下的经验分布来估计p值，无需参数假设但计算成本相对较高68% similarUnverified以英语约5万常用词汇计算，Trigram 理论上需存储约1.25×10¹⁴种组合的概率67% similarUnverified在5%显著性水平下测试100个随机因子，期望会有5个看起来显著（多重假设检验问题）66% similarUnverifiedMin-K% 方法通过检查模型在文本中最低概率token的平均对数概率来判断样本是否为训练集成员66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/740927API
curl https://kongchang.com/api/v1/knowledge/claims/740927MCP
get_claim(id=740927)