diff --git a/src/year2/natural-language-processing/sections/_semantics.tex b/src/year2/natural-language-processing/sections/_semantics.tex
index f0c7e763..220b066 100644
--- a/src/year2/natural-language-processing/sections/_semantics.tex
+++ b/src/year2/natural-language-processing/sections/_semantics.tex
@@ -519,7 +519,7 @@
         \[ \mathcal{L}(\matr{\theta}) = \left( \vec{c} \cdot \vec{w} - \log( \matr{X}[c, w] ) \right)^2 \]
 
         \begin{remark}
-            Empirically, for GloVe it has been observed that the final embedding matrix obtain as $\matr{W} + \matr{C}$ works better.
+            Empirically, for GloVe it has been observed that the final embedding matrix obtained as $\matr{W} + \matr{C}$ works better.
         \end{remark}
 
         \begin{example}