diff --git a/src/year2/natural-language-processing/sections/_rnn.tex b/src/year2/natural-language-processing/sections/_rnn.tex
index 8e540c5..7c19dcd 100644
--- a/src/year2/natural-language-processing/sections/_rnn.tex
+++ b/src/year2/natural-language-processing/sections/_rnn.tex
@@ -33,7 +33,7 @@
     \end{figure}
 
     \begin{remark}
-        RNN-LMs allows to generate the output autoregressively.
+        RNN-LMs allow to generate the output autoregressively.
     \end{remark}
 
     \begin{description}
@@ -98,7 +98,7 @@
         \end{description}
 
         \begin{remark}
-            LSTM makes it easier to preserve information over time, but it might still be affected by the vanishing gradient problem.
+            LSTMs make it easier to preserve information over time, but they might still be affected by the vanishing gradient problem.
         \end{remark}
 
         \begin{figure}[H]
@@ -112,7 +112,7 @@
 
 \begin{description}
     \item[Gated recurrent units (GRU)] \marginnote{Gated recurrent units (GRU)}
-        Architecture simpler than LSTMs with fewer gates and without the cell state.
+        Simpler architecture than LSTMs with fewer gates and without the cell state.
 
         \begin{description}
             \item[Gates] \phantom{}