语言模型的困惑度如何在0和1之间？
[英]How can the perplexity of a language model be between 0 and 1?
问题描述
In Tensorflow, I'm getting outputs like 0.602129 or 0.663941. 
在Tensorflow中，我得到的输出为0.602129或0.663941。 It appears that values closer to 0 imply a better model, but it seems like perplexity is supposed to be calculated as 2^loss, which implies that loss is negative. 似乎值越接近0意味着模型越好，但是似乎困惑应该被计算为2 ^损失，这意味着损失为负。 This doesn't make any sense. 这没有任何意义。
1 个解决方案
解决方案1
1 已采纳 2017-07-02 20:56:18
This does not make a lot of sense to me. 这对我来说没有多大意义。 Perplexity is calculated as 2^entropy . 困惑度被计算为2^entropy 。 And the entropy is from 0 to 1. So your results which are < 1 do not make sense. 熵从0到1。因此，小于1的结果没有意义。
I would suggest you to take a look at how your model calculate the perplexity because I suspect there might be an error. 我建议您看一下您的模型如何计算困惑度，因为我怀疑可能存在错误。
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.