From f4ad3d8ceac6ba74166ba08636eda809b56db3eb Mon Sep 17 00:00:00 2001 From: Joe Davison Date: Thu, 1 Apr 2021 11:58:37 -0600 Subject: [PATCH] minor typo fix *negative* log-likelihood --- docs/source/perplexity.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/source/perplexity.rst b/docs/source/perplexity.rst index 39a1e5ae6c..2ad255e6d9 100644 --- a/docs/source/perplexity.rst +++ b/docs/source/perplexity.rst @@ -18,8 +18,8 @@ that the metric applies specifically to classical language models (sometimes cal models) and is not well defined for masked language models like BERT (see :doc:`summary of the models `). -Perplexity is defined as the exponentiated average log-likelihood of a sequence. If we have a tokenized sequence -:math:`X = (x_0, x_1, \dots, x_t)`, then the perplexity of :math:`X` is, +Perplexity is defined as the exponentiated average negative log-likelihood of a sequence. If we have a tokenized +sequence :math:`X = (x_0, x_1, \dots, x_t)`, then the perplexity of :math:`X` is, .. math::