diff --git a/ignite/metrics/regression/kendall_correlation.py b/ignite/metrics/regression/kendall_correlation.py
index f1dbad5fff8..826ca350ac2 100644
--- a/ignite/metrics/regression/kendall_correlation.py
+++ b/ignite/metrics/regression/kendall_correlation.py
@@ -35,7 +35,7 @@ class KendallRankCorrelation(EpochMetric):
     are said to be concordant when both :math:`P_i<P_j` and :math:`A_i<A_j` holds
     or both :math:`P_i>P_j` and :math:`A_i>A_j`.
 
-    The ``number of discordant pairs`` counts the number of pairs that are not concordant.
+    The `number of discordant pairs` counts the number of pairs that are not concordant.
 
     The computation of this metric is implemented with
     `scipy.stats.kendalltau <https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.kendalltau.html>`_.
diff --git a/ignite/metrics/regression/spearman_correlation.py b/ignite/metrics/regression/spearman_correlation.py
index b57cc63994b..7c5d586b152 100644
--- a/ignite/metrics/regression/spearman_correlation.py
+++ b/ignite/metrics/regression/spearman_correlation.py
@@ -29,7 +29,8 @@ class SpearmanRankCorrelation(EpochMetric):
     .. math::
         r_\text{s} = \text{Corr}[R[P], R[A]] = \frac{\text{Cov}[R[P], R[A]]}{\sigma_{R[P]} \sigma_{R[A]}}
 
-    where :math:`A` and :math:`P` are the ground truth and predicted value, and R[X] is the ranking value of X.
+    where :math:`A` and :math:`P` are the ground truth and predicted value,
+    and :math:`R[X]` is the ranking value of :math:`X`.
 
     The computation of this metric is implemented with
     `scipy.stats.spearmanr <https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.spearmanr.html>`_.